© 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. 7-RESID-POST-AA
    11. 42445
    Prev
    Next
    INDEX
    Explanations

    software

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     aprender
    -0.07
     어
    -0.07
    ＆
    -0.06
    .precision
    -0.06
     jeunes
    -0.06
     GUIStyle
    -0.06
    ำ
    -0.06
    ⽤
    -0.06
    莸
    -0.06
    تحسين
    -0.06
    POSITIVE LOGITS
     Sale
    0.08
    -nil
    0.07
     "))
    0.07
    ali
    0.07
     parity
    0.06
    曷
    0.06
     Nielsen
    0.06
     Surely
    0.06
    淮南
    0.06
    Não
    0.06
    Activations Density 0.003%

    No Known Activations