© 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. 2751
    Prev
    Next
    INDEX
    Explanations

    listing names or specific entities

    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
    å·²è¿ĩ
    -0.07
    kert
    -0.07
    o
    -0.07
    es
    -0.06
    ulk
    -0.06
    eman
    -0.06
    iro
    -0.06
    ×ķ
    -0.06
    \V
    -0.06
    ä¸ĩä¸Ģ
    -0.06
    POSITIVE LOGITS
    inded
    0.08
    شت
    0.08
    trand
    0.08
    tep
    0.08
    åŃIJéĩĮ
    0.08
    quiera
    0.07
    èĩ¥
    0.07
    æĮĩ导建议
    0.07
    _:
    0.07
    inger
    0.07
    Activations Density 0.013%

    No Known Activations