© 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. 48339
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åįķ
    -0.07
    .literal
    -0.07
    åĨ¥
    -0.06
    yron
    -0.06
     afer
    -0.06
    åĮ¿åIJį
    -0.06
    unday
    -0.06
    è´
    -0.06
    cribe
    -0.06
    åįķåIJij
    -0.06
    POSITIVE LOGITS
    \E
    0.07
    [E
    0.07
    CoV
    0.07
    欣
    0.07
    Ä«g
    0.07
    æľīåĵª
    0.07
     thro
    0.07
     Dream
    0.07
    æ¼±åı£
    0.07
    apas
    0.06
    Activations Density 0.000%

    No Known Activations