© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 66759
    Prev
    Next
    INDEX
    Explanations

    plan/idea

    np_max-act · gemini-2.0-flash

    words that indicate forming a plan, idea, decision, or intent (e.g., devising revenge or deciding to act).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .getSharedPreferences
    -0.07
    	step
    -0.07
     infographic
    -0.07
     anxious
    -0.07
     Disneyland
    -0.07
     bibliography
    -0.07
     Fresno
    -0.06
     appliance
    -0.06
     Grocery
    -0.06
     cinematic
    -0.06
    POSITIVE LOGITS
    ותו
    0.07
    аци
    0.07
    _trip
    0.07
    ARING
    0.07
     restTemplate
    0.07
    tones
    0.07
    .g
    0.06
    簡�
    0.06
     NAV
    0.06
    تس
    0.06
    Activations Density 0.114%

    No Known Activations