© 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. 16393
    Prev
    Next
    INDEX
    Explanations

    so please join

    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
    æŃ£ç»ı
    -0.07
    æŀģåħ¶
    -0.07
     heavily
    -0.07
    é¢ľ
    -0.07
    lyn
    -0.06
    åľ¨æŁIJäºĽ
    -0.06
    计æıIJ
    -0.06
    å¿ħé¡»æľī
    -0.06
    è¿ĩ人
    -0.06
    è¿ĺå¿ħé¡»
    -0.06
    POSITIVE LOGITS
    çĽ¸ä¿¡èĩªå·±
    0.10
     your
    0.10
     yourself
    0.10
    è¯ķè¯ķçľĭ
    0.10
     yourselves
    0.10
    your
    0.10
    %!
    0.09
    —you
    0.09
    å±ŀäºİä½łçļĦ
    0.09
    ä½łçļĦæīĭæľº
    0.09
    Activations Density 0.200%

    No Known Activations