© 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. 9413
    Prev
    Next
    INDEX
    Explanations

    file names B.txt, Field, Hugh

    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¸İä¹ĭ
    -0.10
    -extra
    -0.07
    -HT
    -0.07
    ä¸İä»ĸ们
    -0.07
    toa
    -0.07
     tụ
    -0.07
    ä¸İæѤ
    -0.07
    _emb
    -0.07
    æĴ©
    -0.07
    ัà¸ģ
    -0.07
    POSITIVE LOGITS
    æ´Ľä¼Ĭ
    0.08
    çĽ¸å¯¹äºİ
    0.07
    ovid
    0.07
    ä¸Ģä¼ļ
    0.07
    è¾IJ
    0.07
    .console
    0.07
    FromArray
    0.07
    追çĿĢ
    0.07
    çļĦ人è¿ĺ
    0.07
    ä¸Ń继
    0.07
    Activations Density 0.127%

    No Known Activations