© 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. 113757
    Prev
    Next
    INDEX
    Explanations

    code, data tables

    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
    שה
    -0.06
    䁖
    -0.06
     onstage
    -0.06
     stable
    -0.06
    ᔅ
    -0.06
     sticking
    -0.06
    笤
    -0.06
    ｩ
    -0.06
     Sabb
    -0.06
     самостоя
    -0.06
    POSITIVE LOGITS
    otr
    0.08
     physicist
    0.07
    .Footer
    0.07
    运维
    0.07
    SETTINGS
    0.07
     Он
    0.07
    わたし
    0.07
    妳
    0.07
    _redis
    0.07
     voi
    0.07
    Activations Density 0.026%

    No Known Activations