© 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. 79003
    Prev
    Next
    INDEX
    Explanations

    Law

    np_max-act · gemini-2.0-flash

    The neuron detects tokens and phrases referring to legality, illegal or dangerous activities, and policy/ethics-related constraints.

    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
    Zone
    -0.08
    XYZ
    -0.07
    NotificationCenter
    -0.07
     libre
    -0.06
    logue
    -0.06
    .entries
    -0.06
    -loving
    -0.06
    🗡
    -0.06
     LP
    -0.06
     respondent
    -0.06
    POSITIVE LOGITS
    fragistics
    0.07
    人们的
    0.07
    UserCode
    0.06
     sliced
    0.06
     בתח
    0.06
     Cly
    0.06
    עונ
    0.06
    _tF
    0.06
    וגש
    0.06
     Pul
    0.06
    Activations Density 0.040%

    No Known Activations