© 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. 23914
    Prev
    Next
    INDEX
    Explanations

    official followed by a noun

    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¸įå¼ĢçļĦ
    -0.08
    ยà¸Ļà¸ķà¹Į
    -0.07
    æ¯Ķè¾ĥéĢĤåIJĪ
    -0.07
    bieter
    -0.07
    oth
    -0.07
    /rfc
    -0.07
    漪
    -0.07
     Vigo
    -0.07
    íĶĦ
    -0.06
    ten
    -0.06
    POSITIVE LOGITS
    人士
    0.09
    lesia
    0.09
    entas
    0.08
    ÃŃny
    0.08
    ytes
    0.08
    cers
    0.08
    enheim
    0.08
    ằn
    0.08
    lijk
    0.08
    yte
    0.08
    Activations Density 0.054%

    No Known Activations