© 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. 15-RESID-POST-AA
    11. 5609
    Prev
    Next
    INDEX
    Explanations

    DataSource

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    neh
    -0.07
     방문
    -0.07
    讶
    -0.07
    勉
    -0.07
    (train
    -0.06
     Altın
    -0.06
    améli
    -0.06
    娃
    -0.06
     związ
    -0.06
     الاستث
    -0.06
    POSITIVE LOGITS
     composition
    0.07
     posed
    0.07
    事情
    0.07
    次数
    0.07
     quoted
    0.07
     Retrieved
    0.07
     logger
    0.07
     Boulevard
    0.07
     Bayern
    0.06
    magnitude
    0.06
    Activations Density 0.003%

    No Known Activations