© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 71436
    Prev
    Next
    INDEX
    Explanations

    cliff

    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_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
     Greater
    -0.07
    Responder
    -0.07
    .loads
    -0.07
     Soup
    -0.07
    这个时代
    -0.06
    很开心
    -0.06
     mất
    -0.06
     !$
    -0.06
     essa
    -0.06
     modeled
    -0.06
    POSITIVE LOGITS
     CGPoint
    0.08
    _exact
    0.07
    דות
    0.07
    셑
    0.07
    ᨾ
    0.07
     מאחורי
    0.07
    無論
    0.07
     роли
    0.07
     comparatively
    0.06
     TableView
    0.06
    Activations Density 0.003%

    No Known Activations