© 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. 43373
    Prev
    Next
    INDEX
    Explanations

    review option value selected

    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
    ä¸ĩä¸Ģ
    -0.08
     uncomp
    -0.07
    åıªéľĢè¦ģ
    -0.07
    ä¸įçŁ¥éģĵ
    -0.07
    æľī两ç§į
    -0.06
    :key
    -0.06
    /Runtime
    -0.06
    èİ·å¾Ĺ
    -0.06
    两ç§į
    -0.06
    .dtd
    -0.06
    POSITIVE LOGITS
    odos
    0.09
    reck
    0.08
     пÑĢобе
    0.07
    éĢIJä¸Ģ
    0.07
    âĿ
    0.07
    æł¸æŁ¥
    0.07
    尼迪
    0.07
    edah
    0.07
    etros
    0.07
    zás
    0.07
    Activations Density 0.005%

    No Known Activations