© 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. 7932
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and debian

    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
    ajs
    -0.08
    enho
    -0.08
    èĭ±æĸĩ
    -0.08
    ä¸İç¾İåĽ½
    -0.08
    oglob
    -0.07
    лÑİ
    -0.07
    æĶ¾çľ¼
    -0.07
    èĭ±æĸĩåIJį
    -0.07
    DataURL
    -0.07
    ç¾İèĤ¡
    -0.07
    POSITIVE LOGITS
    åľŁå»º
    0.09
    ä¸İåĽ½åĨħ
    0.09
    åĽŀèĢģ家
    0.08
    debian
    0.07
    arris
    0.07
    åľ¨åĽ½åĨħ
    0.07
    天çĽĸ
    0.07
    å°ģ建
    0.07
    ivil
    0.06
    大æĤ²
    0.06
    Activations Density 0.726%

    No Known Activations