© 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. 13794
    Prev
    Next
    INDEX
    Explanations

    compute, create, calculate, buy

    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
    åĩºäºĨä¸Ģ
    -0.06
     repos
    -0.06
    uset
    -0.06
    op
    -0.06
    ä¸Ĭ人
    -0.06
    ContentSize
    -0.06
    oskop
    -0.06
    enson
    -0.06
    cascade
    -0.06
    st
    -0.05
    POSITIVE LOGITS
    ä¸įæīĵ
    0.08
    æĭīæĭī
    0.07
    çĺ©
    0.07
    ickers
    0.07
    ozilla
    0.07
    ä¸įæķ¢
    0.07
    éĿ¡
    0.07
    ocoder
    0.07
    å¾·æĭī
    0.07
    ä¸įæĩĤå¾Ĺ
    0.07
    Activations Density 0.001%

    No Known Activations