© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44707
    Prev
    Next
    INDEX
    Explanations

    rate of

    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
    Negative Logits
    onnier
    -0.08
    lette
    -0.07
    äºļçī¹
    -0.07
    idden
    -0.07
    aille
    -0.07
    alin
    -0.07
    alian
    -0.07
    éĿĴå±±
    -0.06
    æĸ¯çī¹
    -0.06
    /********************************************************
    -0.06
    POSITIVE LOGITS
    è¡ħ
    0.07
    请å°Ĩ
    0.07
    ivor
    0.07
    大åij¼
    0.07
    èĩ´ä»¥
    0.07
    åŃľåŃľ
    0.06
    inst
    0.06
    دار
    0.06
    æľīå¤ļ大
    0.06
    -Identifier
    0.06
    Activations Density 0.003%

    No Known Activations