© 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. 15-RESID-POST-AA
    11. 82317
    Prev
    Next
    INDEX
    Explanations

    Date

    np_max-act · gemini-2.0-flash
    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
     matter
    -0.08
    ableObject
    -0.07
    oriously
    -0.07
     context
    -0.07
    客商
    -0.07
    ואר
    -0.07
    (mContext
    -0.07
     tcb
    -0.07
     ther
    -0.07
    indexed
    -0.06
    POSITIVE LOGITS
    ⛷
    0.07
     participated
    0.06
    改善
    0.06
     hollow
    0.06
    :nil
    0.06
     insults
    0.06
     gunshot
    0.06
     negligible
    0.06
    /animate
    0.06
     benefici
    0.06
    Activations Density 0.011%

    No Known Activations