© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48681
    Prev
    Next
    INDEX
    Explanations

    factors, structure, degree, risk, metals

    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
    igna
    -0.07
    éĩij马
    -0.06
    ived
    -0.06
    aza
    -0.06
    osit
    -0.06
    欣
    -0.06
    _ext
    -0.06
    igno
    -0.06
    Matchers
    -0.06
    å«£
    -0.06
    POSITIVE LOGITS
    æ¯Ķåݻ年åIJĮæľŁ
    0.08
    顺åĪ©
    0.08
    istar
    0.08
    åľ¨æŃ¤æ¬¡
    0.08
    çĶ¨çº¸
    0.07
    .hh
    0.07
    anz
    0.07
    .pretty
    0.07
    详ç»Ĩåľ°åĿĢ
    0.07
    êu
    0.07
    Activations Density 0.002%

    No Known Activations