© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    To introduce a phrase or action

    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
    ients
    -0.08
    ãģįãģ£ãģ¨
    -0.08
    ymp
    -0.08
    loquent
    -0.08
    icious
    -0.07
    ìĦľ
    -0.07
    ãģ©ãĤĵãģ©ãĤĵ
    -0.07
    udel
    -0.07
    æ²ĥæĸ¯
    -0.07
    leans
    -0.07
    POSITIVE LOGITS
    èµ·è§ģ
    0.13
    究åħ¶åİŁåĽł
    0.08
    æĸ°åĬłåĿ¡
    0.08
    ething
    0.07
    fino
    0.07
    çļĦç¼ĺæķħ
    0.07
    ÃŃso
    0.07
    oro
    0.07
    æĪIJ为ä¸ĢåIJį
    0.07
    èĢĮ代ä¹ĭ
    0.07
    Activations Density 0.087%

    No Known Activations