© 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. 108111
    Prev
    Next
    INDEX
    Explanations

    /

    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
     rookie
    -0.07
    🤓
    -0.07
    ≅
    -0.07
     Ngô
    -0.07
     soldier
    -0.07
     Rosenstein
    -0.07
     Cleveland
    -0.07
     как
    -0.07
     contestant
    -0.07
     организации
    -0.07
    POSITIVE LOGITS
     /
    0.12
    /
    0.12
    /G
    0.08
    /(
    0.08
     차
    0.07
    Discovery
    0.07
     `/
    0.07
    Blend
    0.07
     /\
    0.07
     바랍
    0.07
    Activations Density 0.354%

    No Known Activations