© 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. 130357
    Prev
    Next
    INDEX
    Explanations

    1 or 0

    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
    .Util
    -0.07
    Looks
    -0.07
    <boost
    -0.07
     Polish
    -0.07
    EMS
    -0.07
     提
    -0.07
    -sharing
    -0.06
     Maxim
    -0.06
    .Line
    -0.06
    统筹推进
    -0.06
    POSITIVE LOGITS
     wakeup
    0.07
    呛
    0.07
     nudity
    0.07
     Hussein
    0.06
     Maison
    0.06
    みたい
    0.06
    特色社会
    0.06
     screenSize
    0.06
    _Generic
    0.06
     phí
    0.06
    Activations Density 0.000%

    No Known Activations