© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12317
    Prev
    Next
    INDEX
    Explanations

    names of places and teams

    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
    acci
    -0.07
    Äĥm
    -0.06
    ç¡Ģ
    -0.06
    sett
    -0.06
    º
    -0.06
     Tog
    -0.06
    rup
    -0.06
    зам
    -0.06
    segn
    -0.06
    mad
    -0.06
    POSITIVE LOGITS
    /ubuntu
    0.07
    alik
    0.07
    éģĵè¿ľ
    0.07
    unday
    0.07
    åħ´åįİ
    0.07
     اÙĦÙħÙĥر
    0.07
    uches
    0.07
    Ñģнабжение
    0.07
    achi
    0.07
    åĽ½ç«ĭ
    0.07
    Activations Density 0.002%

    No Known Activations