© 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. 11-RESID-POST-AA
    11. 112271
    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
     abuses
    -0.07
    uncture
    -0.07
    热播
    -0.07
    万余元
    -0.07
    ڴ
    -0.07
     zijn
    -0.07
    (add
    -0.07
     obsessive
    -0.06
    typeparam
    -0.06
    ʶ
    -0.06
    POSITIVE LOGITS
    水面
    0.07
    -like
    0.07
    sci
    0.07
     plasma
    0.07
     dash
    0.06
     "="
    0.06
    豆浆
    0.06
    igu
    0.06
    D
    0.06
     rotate
    0.06
    Activations Density 0.008%

    No Known Activations