© 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. 25529
    Prev
    Next
    INDEX
    Explanations

    regardless of

    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
    èĢĮä¸įæĺ¯
    -0.08
    èĢĮéĿŀ
    -0.07
    NOT
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
     NOT
    -0.07
    ä¸įåĪĨ
    -0.07
    oland
    -0.07
    åı¯æľŁ
    -0.07
    ä¸įä»ħåľ¨
    -0.07
    غ
    -0.06
    POSITIVE LOGITS
     nor
    0.11
     sekalipun
    0.11
    大ä¸įäºĨ
    0.10
    ä¸İåIJ¦
    0.10
    èĢĮåľ¨äºİ
    0.10
     whatsoever
    0.09
    à¸ģà¹ĩà¸ķาม
    0.09
    Whether
    0.09
     Whether
    0.09
    ä½Ĩåıªè¦ģ
    0.09
    Activations Density 0.097%

    No Known Activations