© 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. 50817
    Prev
    Next
    INDEX
    Explanations

    character type declaration

    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
     privately
    -0.08
    æ¯ĭ
    -0.06
     private
    -0.06
     Scr
    -0.06
    ç§ģ
    -0.06
    æµģå¹´
    -0.06
    ernaut
    -0.06
    æĸ¹éĿ¢
    -0.06
    æīĢèĥ½
    -0.06
    fern
    -0.06
    POSITIVE LOGITS
     simpler
    0.15
    ç®ĢåįķçļĦ
    0.13
    åįĺç´Ķ
    0.13
    æľĢç®Ģåįķ
    0.12
     plain
    0.12
    æľĢç®ĢåįķçļĦ
    0.12
    åįķ纯çļĦ
    0.12
    ç®Ģåįķ
    0.12
    Plain
    0.12
     simplest
    0.12
    Activations Density 0.248%

    No Known Activations