© 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. 44457
    Prev
    Next
    INDEX
    Explanations

    .com domain and file types

    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
    Negative Logits
    rika
    -0.08
    rer
    -0.08
    zza
    -0.07
    moth
    -0.07
    riger
    -0.07
    cko
    -0.07
    ampi
    -0.07
    riz
    -0.07
    zug
    -0.07
    è¿ĺæľª
    -0.07
    POSITIVE LOGITS
    anson
    0.07
    aspx
    0.07
    amespace
    0.07
     Dossier
    0.07
    osu
    0.06
    éģĵè¿ľ
    0.06
    è¾¾åħĭ
    0.06
    igheden
    0.06
    ä¸įä¼ij
    0.06
    ç²ķ
    0.06
    Activations Density 0.015%

    No Known Activations