© 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. 46852
    Prev
    Next
    INDEX
    Explanations

    window creation and bounds

    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
    è¿Ļ两ç§į
    -0.07
    两ç§įæĸ¹å¼ı
    -0.07
    avn
    -0.06
    两ç§į
    -0.06
    ä¸Ģç§įæĺ¯
    -0.06
    æľī两ç§į
    -0.06
    è¿Ļ两个
    -0.06
    çŃł
    -0.06
     gr
    -0.06
    Both
    -0.05
    POSITIVE LOGITS
    ?,?,?,?,
    0.15
    ?,?,
    0.11
    ãĢģãĢģãĢģ
    0.10
    æĺ¥å¤ıç§ĭåĨ¬
    0.09
    ãĢģãĢģ
    0.09
    ','','
    0.09
    åīįä¸ī
    0.09
    åĽĽå±Ĥ
    0.08
    agara
    0.08
    letal
    0.08
    Activations Density 0.134%

    No Known Activations