© 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. 22413
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    tures
    -0.09
    ingly
    -0.09
    åĪ°å¤§
    -0.08
    ancy
    -0.08
    istration
    -0.08
    eral
    -0.08
    eding
    -0.07
    ighbors
    -0.07
    anced
    -0.07
    edException
    -0.07
    POSITIVE LOGITS
    en
    0.16
    Ùĩ
    0.15
    èĩªå·±
    0.12
    ä¼ĹæīĢåij¨çŁ¥
    0.12
    ÛĮ
    0.12
    缸è¾ħ缸æĪIJ
    0.12
    ed
    0.12
    ä¸įåı¯æĢĿè®®
    0.11
    gether
    0.11
    ÙģÙĪظ
    0.11
    Activations Density 0.026%

    No Known Activations