© 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. 26641
    Prev
    Next
    INDEX
    Explanations

    system structure

    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
     merged
    -0.07
    ipper
    -0.07
    лиз
    -0.06
    rup
    -0.06
     exclus
    -0.06
    ä½ľåĩºçļĦ
    -0.06
    atte
    -0.06
     Conway
    -0.06
     prestig
    -0.06
    è¿Ļ两ç§į
    -0.06
    POSITIVE LOGITS
    ä¸īéĥ¨æĽ²
    0.15
    ä¸īæŃ¥
    0.14
    è¦ģç´ł
    0.13
    ä¸īå±Ĥ
    0.12
    ä¸īéĥ¨åĪĨ
    0.12
    åĽĽå±Ĥ
    0.12
    缺ä¸Ģä¸įåı¯
    0.11
    ä¸ī级
    0.11
    ä¸ī段
    0.11
     structure
    0.11
    Activations Density 0.286%

    No Known Activations