© 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. 32777
    Prev
    Next
    INDEX
    Explanations

    as follows

    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
    ä¼ĺåĬ¿çļĦ
    -0.07
    ARGS
    -0.07
    plusplus
    -0.07
    Hashtable
    -0.07
    é¢Ĺç²Ĵ
    -0.07
    è¦ģ强
    -0.07
    .nb
    -0.07
    ursal
    -0.07
    anto
    -0.07
    ä»·å·®
    -0.07
    POSITIVE LOGITS
    ately
    0.06
    apping
    0.06
    âĶĤ
    0.06
    adu
    0.06
    unsch
    0.06
    à®±à¯įà®±à¯ģ
    0.06
    uv
    0.06
    éĻ
    0.06
    请éĹ®
    0.06
    éĮ¯
    0.06
    Activations Density 0.083%

    No Known Activations