© 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. 7592
    Prev
    Next
    INDEX
    Explanations

    asking questions

    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
    rive
    -0.09
    ä¸įæĺ¯ä»Ģä¹Ī
    -0.08
    rup
    -0.08
    è¦ģä¸įæĺ¯
    -0.07
    æĺ¯æĢİä¹Ī
    -0.07
    ighed
    -0.07
    estead
    -0.07
    rong
    -0.07
    _UTF
    -0.06
    erot
    -0.06
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
    羣çļĦ
    0.10
    è¿ĺæľīåħ¶ä»ĸ
    0.10
     acaso
    0.09
    æŀľçľŁ
    0.09
    羣çļĦæľī
    0.09
     ever
    0.09
     necessarily
    0.08
     something
    0.08
     anything
    0.08
    Activations Density 0.313%

    No Known Activations