© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50223
    Prev
    Next
    INDEX
    Explanations

    +, signs, and scientific notation

    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
    lor
    -0.08
    ements
    -0.08
    lsi
    -0.08
    uce
    -0.08
    cion
    -0.08
    casts
    -0.08
    ncy
    -0.07
    ezo
    -0.07
    cast
    -0.07
    uve
    -0.07
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.15
    åĭĩå¾Ģ缴åīį
    0.14
    äºĭåįĬåĬŁåĢį
    0.13
    身临åħ¶å¢ĥ
    0.13
    åĬłæĭ¿å¤§
    0.13
    两åѦä¸Ģåģļ
    0.12
    缸è¾ħ缸æĪIJ
    0.12
    ä¼ĹæīĢåij¨çŁ¥
    0.12
    æĸ°åĬłåĿ¡
    0.11
    ìķ¼
    0.10
    Activations Density 0.191%

    No Known Activations