© 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. 29396
    Prev
    Next
    INDEX
    Explanations

    arges with çīĪ

    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
    æĻĹ
    -0.07
     intrig
    -0.07
    wat
    -0.07
    benh
    -0.07
    ek
    -0.07
    ezd
    -0.07
    ابÙĦ
    -0.07
    urname
    -0.07
    utti
    -0.07
    ngr
    -0.07
    POSITIVE LOGITS
    jiang
    0.07
    輪
    0.07
    æł
    0.07
    ç¯ī
    0.06
    manship
    0.06
    å¬
    0.06
     dang
    0.06
     Beit
    0.06
    fels
    0.06
     rep
    0.06
    Activations Density 0.002%

    No Known Activations