© 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. 34533
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code delimiters (

    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
    ä½łè¿ĺæĺ¯
    -0.06
     Parade
    -0.06
    æĹ¢åı¯ä»¥
    -0.06
    czyn
    -0.06
     _
    -0.06
     Thorn
    -0.06
     either
    -0.06
     dew
    -0.05
    spar
    -0.05
    ä¸įä»ħåı¯ä»¥
    -0.05
    POSITIVE LOGITS
    缴éĢļ
    0.10
     altrettanto
    0.09
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.08
    ÃŃÄį
    0.08
    çŃīåħ¶ä»ĸ
    0.08
    ä¸įæĪIJ
    0.08
     lainnya
    0.08
     sonstige
    0.08
    á»ijn
    0.08
    egram
    0.08
    Activations Density 0.036%

    No Known Activations