© 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. 10389
    Prev
    Next
    INDEX
    Explanations

    help me

    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¸Ģè¯ķ
    -0.09
     کرد
    -0.08
    äºĨè¿Ľåİ»
    -0.07
    æĬ¥è®¯
    -0.07
    åĪĨ享ç»Ļ大家
    -0.07
    è¾¾æĸ¯
    -0.07
    è´¡
    -0.07
    ames
    -0.07
    zah
    -0.07
    vaa
    -0.07
    POSITIVE LOGITS
    umble
    0.07
    åķ¬
    0.06
    æĽĻ
    0.06
     McMahon
    0.06
    argon
    0.06
    /meta
    0.06
    à¸Ĥา
    0.06
    æĸ¹éĿ¢æľī
    0.06
    RP
    0.06
    åĵªæĢķ
    0.06
    Activations Density 0.002%

    No Known Activations