© 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. 8924
    Prev
    Next
    INDEX
    Explanations

    pier, stimulus, assailant, shooter, suspects

    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
    ä¸į缺
    -0.07
    èݱæĸ¯
    -0.07
    ILA
    -0.07
    ç¼Ŀ
    -0.06
    conversion
    -0.06
    马ä¸Ĭ
    -0.06
    缩åĩı
    -0.06
    _convert
    -0.06
    转æį¢
    -0.06
     Gros
    -0.06
    POSITIVE LOGITS
    ounter
    0.08
    ä¼łäºº
    0.08
    istar
    0.07
    ä½łçļĦåIJįåŃĹ
    0.07
    æĨ
    0.07
    ç»Ħç»ĩå®ŀæĸ½
    0.07
    пÑĢÑĥ
    0.07
    xit
    0.07
    åĪĨåĪ«ä¸İ
    0.07
    inia
    0.07
    Activations Density 0.003%

    No Known Activations