© 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. 81503
    Prev
    Next
    INDEX
    Explanations

    magnetic

    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
    Not in Any Lists

    No Comments

    Negative Logits
    忳
    -0.08
    何必
    -0.07
    妥善
    -0.07
     tutorial
    -0.07
    ተ
    -0.07
    导读
    -0.06
     babel
    -0.06
    때
    -0.06
     Jason
    -0.06
     hardship
    -0.06
    POSITIVE LOGITS
    褡
    0.08
    shoot
    0.07
    占据
    0.07
    yor
    0.07
    这支
    0.07
    foreach
    0.07
    _ant
    0.07
     프
    0.07
    &nbsp
    0.07
    ┋
    0.06
    Activations Density 0.008%

    No Known Activations