© 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. 29536
    Prev
    Next
    INDEX
    Explanations

    by followed by quantity

    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
    åľ¨æĪijå¿ĥä¸Ń
    -0.08
    berger
    -0.08
    à«į
    -0.07
    nex
    -0.07
    起家
    -0.07
    æķĻèĤ²å®ŀ践活åĬ¨
    -0.07
    æŀģå°ijæķ°
    -0.07
    ä¸ĬåĽ¾
    -0.07
     Bras
    -0.07
     esclus
    -0.07
    POSITIVE LOGITS
    /remove
    0.07
    ilter
    0.07
    åįĵ
    0.07
     rá»ĩt
    0.07
    æĥ¨éĩį
    0.07
    è¾Ī
    0.07
    çļĦç¨ĭ度
    0.07
    ведением
    0.06
    èĢĮéĻį
    0.06
    åĩĽ
    0.06
    Activations Density 0.070%

    No Known Activations