© 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. 17393
    Prev
    Next
    INDEX
    Explanations

    "I" followed by question/statement

    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
    atte
    -0.07
    Ïİ
    -0.07
    常çĶ¨
    -0.07
    ç»ĻæĪij们带æĿ¥
    -0.07
    umb
    -0.07
    anz
    -0.07
    ĮĢ
    -0.07
    omor
    -0.07
    quo
    -0.07
    æ£
    -0.06
    POSITIVE LOGITS
    ento
    0.06
     calibre
    0.06
    ë¶Ģ를
    0.06
    yä
    0.06
    -db
    0.06
    HandlerContext
    0.06
    ä¾Ī
    0.06
    egas
    0.06
    PACE
    0.06
    ëĭ¤ëĬĶ
    0.06
    Activations Density 0.918%

    No Known Activations