© 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. 12239
    Prev
    Next
    INDEX
    Explanations

    onic

    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
    报社
    -0.07
    estar
    -0.07
    locker
    -0.06
     fopen
    -0.06
    zbollah
    -0.06
    getConfig
    -0.06
    開展
    -0.06
    莪
    -0.06
    already
    -0.06
    Bias
    -0.06
    POSITIVE LOGITS
     approximate
    0.07
    ätz
    0.07
     amazed
    0.06
    惨
    0.06
     shiny
    0.06
    ´s
    0.06
     abundant
    0.06
    的基本
    0.06
    iniz
    0.06
     Authentic
    0.06
    Activations Density 0.002%

    No Known Activations