© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10958
    Prev
    Next
    INDEX
    Explanations

    hen, way, different, oft, apparent, case

    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
    涩
    -0.07
     otherwise
    -0.06
    æ
    -0.06
    lements
    -0.06
     either
    -0.06
    /dev
    -0.06
    upal
    -0.06
    emuk
    -0.06
    xim
    -0.06
    æk
    -0.06
    POSITIVE LOGITS
     Hag
    0.07
    åĮħçļĦ
    0.07
    ãĥĸãĥŃãĤ°æĿij
    0.07
     infamous
    0.07
    广大çļĦ
    0.07
     Drop
    0.07
    ç»ıæµİè¿IJè¡Į
    0.07
     .**
    0.07
    ç»ıæµİåŃ¦å®¶
    0.07
    доми
    0.07
    Activations Density 0.037%

    No Known Activations