© 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. 41524
    Prev
    Next
    INDEX
    Explanations

    amount of integer

    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
    ãĤ¹ãĥ¡
    -0.07
    èĦĬæ¢ģ
    -0.07
    ernel
    -0.07
    apesh
    -0.07
    identes
    -0.07
    elat
    -0.07
    íĺ¼
    -0.07
    leiding
    -0.07
    ä¸īéĩĮ
    -0.07
    лий
    -0.07
    POSITIVE LOGITS
    _Integer
    0.08
    egl
    0.07
    å¥ĩ
    0.07
    礼
    0.07
    uber
    0.07
    åľ¨åįĬ
    0.07
     generous
    0.07
     copies
    0.07
    禮
    0.07
    erk
    0.06
    Activations Density 0.002%

    No Known Activations