© 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. 43725
    Prev
    Next
    INDEX
    Explanations

    number of games

    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
     phá»ķ
    -0.06
     Kud
    -0.06
    èĩªè¨Ģ
    -0.06
     Kitt
    -0.06
    åĮħéĩĮ
    -0.06
    éĻĦæľī
    -0.06
    à¹Ģà¸Ķียว
    -0.06
    è£ģå®ļ
    -0.06
    лез
    -0.06
    ä¸į失
    -0.06
    POSITIVE LOGITS
    å¢Ł
    0.08
    бли
    0.08
    åĨ¶
    0.07
    unga
    0.07
    apg
    0.07
    å¾·æĭī
    0.07
    azah
    0.07
    éĦ
    0.07
    getAs
    0.07
    aska
    0.07
    Activations Density 0.003%

    No Known Activations