© 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. 48218
    Prev
    Next
    INDEX
    Explanations

    beautiful descriptions

    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
    oya
    -0.08
    ünstler
    -0.08
    abr
    -0.07
    é»Ħé¾Ļ
    -0.07
    erschaft
    -0.07
    (GLFW
    -0.07
    ä¸į稳
    -0.07
    èĥ½èĢIJ
    -0.07
    åľ°æļĸ
    -0.07
     ossia
    -0.07
    POSITIVE LOGITS
    ç»Ŀ伦
    0.11
    ening
    0.09
    丽çļĦ
    0.09
    åĬ¨äººçļĦ
    0.08
    ä½³èĤ´
    0.08
    iose
    0.08
    θÏį
    0.07
    æĹłçijķ
    0.07
    ä»·å»ī
    0.07
    åĵī
    0.07
    Activations Density 0.061%

    No Known Activations