© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    punctuation or separators

    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
    PointerException
    -0.11
    ت
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    egers
    -0.09
    gers
    -0.09
    relude
    -0.09
    asticsearch
    -0.09
    tures
    -0.09
    esz
    -0.09
    culares
    -0.08
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.19
    ly
    0.18
    a
    0.18
    åĭĩå¾Ģ缴åīį
    0.17
    o
    0.13
    ا
    0.13
    åĬłæĭ¿å¤§
    0.13
    æĸ°åĬłåĿ¡
    0.12
    ä¸įåı¯æĢĿè®®
    0.12
    äºĭåįĬåĬŁåĢį
    0.12
    Activations Density 0.003%

    No Known Activations