© 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. 19818
    Prev
    Next
    INDEX
    Explanations

    lipoprotein

    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
    lical
    -0.08
    åIJIJ
    -0.07
    åıĺæļĸ
    -0.07
     lave
    -0.07
    unts
    -0.07
    ä¸ĢåºĶ
    -0.07
    uben
    -0.06
    isty
    -0.06
    ournal
    -0.06
    &view
    -0.06
    POSITIVE LOGITS
    å¬ī
    0.08
    ä¸ĭ课
    0.08
    ç«ĭéĿ¢
    0.07
    lse
    0.07
    ioni
    0.07
    unga
    0.07
    ahir
    0.07
    éľĦ
    0.07
    bookmark
    0.07
     Sod
    0.07
    Activations Density 0.072%

    No Known Activations