© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 113578
    Prev
    Next
    INDEX
    Explanations

    on

    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
    Negative Logits
     stormed
    -0.07
    /X
    -0.07
    sel
    -0.07
     já
    -0.06
    绲
    -0.06
     --------------------
    -0.06
     xAxis
    -0.06
     tut
    -0.06
     خ
    -0.06
     вн
    -0.06
    POSITIVE LOGITS
    千万不要
    0.07
     delegated
    0.07
    查看全文
    0.07
    维奇
    0.07
    积极配合
    0.07
     biscuits
    0.07
     frequently
    0.07
    万美元
    0.07
    慣
    0.07
    体力
    0.07
    Activations Density 0.001%

    No Known Activations