© 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. 43528
    Prev
    Next
    INDEX
    Explanations

    ". "

    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
    icky
    -0.08
    ç´¯çļĦ
    -0.08
    ush
    -0.08
    ukk
    -0.08
    ulet
    -0.08
    Ymd
    -0.08
    stab
    -0.08
    å¡ļ
    -0.08
    åı£æ°´
    -0.07
    olik
    -0.07
    POSITIVE LOGITS
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    onha
    0.08
    以åıĬåħ¶ä»ĸ
    0.07
    on
    0.06
    heiros
    0.06
    erox
    0.06
    éĢļè¿ĩåIJİ
    0.06
    Ø¡
    0.06
    çĶŁæķĪåIJİ
    0.06
    ×Ļ×Ŀ
    0.06
    Activations Density 0.012%

    No Known Activations