© 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. 13360
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or parenthesis

    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
    _CHARSET
    -0.08
    handel
    -0.07
    ieux
    -0.07
    actus
    -0.07
    orio
    -0.07
    ÃŃdio
    -0.07
    itia
    -0.07
    entin
    -0.07
    _DET
    -0.07
    ertino
    -0.07
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    åIJĦç§įåIJĦæł·
    0.07
    çľģçķ¥
    0.07
    äºĭåįĬåĬŁåĢį
    0.07
    on
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    oj
    0.07
    åIJĦç§įåIJĦæł·çļĦ
    0.06
    ipan
    0.06
    Activations Density 0.008%

    No Known Activations