© 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. 33633
    Prev
    Next
    INDEX
    Explanations

    drawing and graphics APIs

    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
     termin
    -0.07
     radio
    -0.07
     spine
    -0.07
     accordion
    -0.06
    ariat
    -0.06
    åı£è¯Ń
    -0.06
    èĢ³èģĭ
    -0.06
    骡
    -0.06
    åĵįèµ·
    -0.06
    æīĭ串
    -0.06
    POSITIVE LOGITS
    rawing
    0.09
     efficac
    0.08
     pixels
    0.08
    pixels
    0.08
    éĿ¢ç§¯
    0.08
     menghal
    0.08
    .drawRect
    0.08
    imitives
    0.08
    ceau
    0.08
    ç»ĺåĪ¶
    0.08
    Activations Density 0.157%

    No Known Activations