© 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 EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 113918
    Prev
    Next
    INDEX
    Explanations

    online discussions

    np_max-act · gemini-2.0-flash

    messages or tokens associated with abusive, hateful, violent, or other policy-violating user requests (safety-triggering content).

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ú
    -0.07
    .success
    -0.06
    奏
    -0.06
    -present
    -0.06
    思
    -0.06
    יית
    -0.06
    Monitor
    -0.06
    泅
    -0.06
    律
    -0.06
    .reject
    -0.06
    POSITIVE LOGITS
     Deutschland
    0.08
     While
    0.07
    �
    0.07
    ITIONS
    0.07
     qualitative
    0.07
     المرأة
    0.07
     europé
    0.07
    .gallery
    0.07
     المناطق
    0.07
     الانتخابات
    0.07
    Activations Density 0.091%

    No Known Activations