© 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. 12915
    Prev
    Next
    INDEX
    Explanations

    sensing and detection devices

    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
     Scol
    -0.07
    ×ķ×ļ
    -0.07
    elib
    -0.07
    ìļ´
    -0.07
    ako
    -0.06
    ually
    -0.06
    æ·ĭæ¼ĵå°½
    -0.06
    awali
    -0.06
     levering
    -0.06
    ìĭľë¡ľ
    -0.06
    POSITIVE LOGITS
    设äºİ
    0.12
    çŃī设å¤ĩ
    0.11
     strategically
    0.10
    è®¾ç½®åľ¨
    0.10
    å®īè£ħåľ¨
    0.10
    ä½įäºİ
    0.10
    è®¾åľ¨
    0.10
    åĪĨå¸ĥåľ¨
    0.09
    æĶ¾ç½®åľ¨
    0.09
    æīĢåľ¨çļĦä½įç½®
    0.09
    Activations Density 0.259%

    No Known Activations