© 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. 108834
    Prev
    Next
    INDEX
    Explanations

    fast

    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
    整理
    -0.07
     tĩnh
    -0.07
     cancer
    -0.07
    端午
    -0.07
    只为
    -0.07
    disp
    -0.07
     Manufacturing
    -0.07
    -th
    -0.06
    ☡
    -0.06
    ForResult
    -0.06
    POSITIVE LOGITS
    (ui
    0.08
     להגיע
    0.07
     hız
    0.07
     rápida
    0.07
     behaves
    0.07
     quickly
    0.06
     fastest
    0.06
    .OrderBy
    0.06
    ⠀
    0.06
     bleach
    0.06
    Activations Density 0.117%

    No Known Activations