© 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. 40267
    Prev
    Next
    INDEX
    Explanations

    release candidates and betas

    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
    ugo
    -0.09
    /Images
    -0.09
    åĮºåĮº
    -0.08
    istrar
    -0.08
    ä¸ŃæĭĽ
    -0.07
    /Image
    -0.07
    ushman
    -0.07
    /Page
    -0.07
    mand
    -0.07
    è¿ĩå¢ĥ
    -0.07
    POSITIVE LOGITS
    稿
    0.12
    èįī稿
    0.10
    éĺ¶æ®µçļĦ
    0.10
    æĪĸæľª
    0.10
    æľªå®ĮæĪIJ
    0.10
    æľªç»ı
    0.10
    段éļİ
    0.10
    稿件
    0.09
     pending
    0.09
     prelim
    0.09
    Activations Density 0.327%

    No Known Activations