© 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. 39243
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    æĢ»èĢĮè¨Ģä¹ĭ
    -0.08
    Lite
    -0.07
    akedown
    -0.07
    cision
    -0.07
    ousel
    -0.07
    å§Ĩæĸ¯
    -0.07
    æīį
    -0.07
    ulang
    -0.07
    æīįåı¯
    -0.07
    Chars
    -0.07
    POSITIVE LOGITS
    æĹ©éĢŁ
    0.07
    à¸į
    0.06
    稼
    0.06
    berra
    0.06
    éĢļ
    0.06
    ...
    0.06
    æĺ¯åIJ¦ä¸İ
    0.06
    ç»
    0.06
    é«ĺ人
    0.06
    ort
    0.06
    Activations Density 0.198%

    No Known Activations