© 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. 20576
    Prev
    Next
    INDEX
    Explanations

    stain removal

    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
    积æŀģç»Ħç»ĩ
    -0.07
    ä¸Ĭ马
    -0.07
    缴æİ¥æĪĸ
    -0.07
    Tes
    -0.07
    æĬ½åĩº
    -0.06
    æ¯ĶæĻ®éĢļ
    -0.06
     بÙĬد
    -0.06
    brem
    -0.06
    åĮ¿åIJį
    -0.06
    æŃ£åıį
    -0.06
    POSITIVE LOGITS
    SSIP
    0.09
    æİ¥åıĹäºĨ
    0.08
     Accept
    0.08
    åıªæ±Ĥ
    0.08
     acept
    0.08
    ä¸įåľ¨ä¹İ
    0.08
    .Accept
    0.08
     acceptance
    0.08
    åıªå¥½
    0.08
    并ä¸įéľĢè¦ģ
    0.08
    Activations Density 0.112%

    No Known Activations