© 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. 47943
    Prev
    Next
    INDEX
    Explanations

    halfway point

    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
    irman
    -0.08
    utsch
    -0.08
    lrt
    -0.08
    好å¿ĥæĥħ
    -0.07
    igans
    -0.07
    fels
    -0.07
    à¹Ģà¸Ľà¸¥
    -0.07
    elman
    -0.07
    ÖĢ
    -0.07
    ocker
    -0.07
    POSITIVE LOGITS
    ±
    0.07
    pm
    0.06
    ä¸Ģæĸ¹
    0.06
     Hear
    0.06
    ä¸ĢåįĬ
    0.06
    è¿ĩåįĬ
    0.06
    æĹ¢åı¯
    0.06
    ä¸Ģæĸ¹çļĦ
    0.06
    æľīæĿ¡ä¸įç´Ĭ
    0.06
    éķ¿ä¹IJ
    0.06
    Activations Density 0.007%

    No Known Activations