© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60053
    Prev
    Next
    INDEX
    Explanations

    RS. CRORES

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     %+
    -0.07
    Disallow
    -0.07
    -schema
    -0.07
    arr
    -0.07
    åĬ
    -0.07
    åħľ
    -0.07
    hai
    -0.06
    æ½®
    -0.06
    èİ·èµł
    -0.06
    åħ«åŃĹ
    -0.06
    POSITIVE LOGITS
    elang
    0.09
    sene
    0.08
    à¹Īาย
    0.08
    .imp
    0.08
    符
    0.07
    ATRIX
    0.07
    ialized
    0.07
    Ø·ÙĬÙĨ
    0.07
    /member
    0.07
    Scaler
    0.07
    Activations Density 0.009%

    No Known Activations