© 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. 63457
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    设å¤ĩçŃī
    -0.07
    otti
    -0.07
    aza
    -0.07
    åIJ¬å®Į
    -0.07
    åįİçļĦ
    -0.06
    åī©ä¸ĭ
    -0.06
    aw
    -0.06
    credi
    -0.06
    aint
    -0.06
    åĽļ
    -0.06
    POSITIVE LOGITS
    ä¸įä½Ĩ
    0.10
    ä¸įä»ħåľ¨
    0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.08
    æĹ¢æĺ¯
    0.08
    ä¸įåĥħ
    0.08
    ä¸Ģæĸ¹éĿ¢
    0.08
    è¿Ļä¸įä»ħ
    0.08
    ä¸įä»ħ
    0.08
    ä¸įä»ħèĥ½
    0.08
    stored
    0.08
    Activations Density 0.195%

    No Known Activations