© 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. 7-RESID-POST-AA
    11. 78714
    Prev
    Next
    INDEX
    Explanations

    desp

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _curr
    -0.07
     当
    -0.07
    认清
    -0.07
     Comp
    -0.07
     Stop
    -0.07
     gonna
    -0.07
    elsif
    -0.07
    躺在
    -0.07
    irlines
    -0.07
    .to
    -0.07
    POSITIVE LOGITS
    暮ら
    0.07
    .yahoo
    0.07
     있으며
    0.07
    㭕
    0.07
     basin
    0.07
    ETIME
    0.07
    عبارة
    0.07
    STRACT
    0.06
    mayı
    0.06
    ueil
    0.06
    Activations Density 0.001%

    No Known Activations