© 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. 49361
    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
    kaar
    -0.10
    iguez
    -0.08
    IGIN
    -0.08
    åĽ
    -0.08
    æ¯ĽçĹħ
    -0.07
    .statusText
    -0.07
    .scalar
    -0.07
    á»ĵng
    -0.07
    æľ¬æĸĩ为åįļ主
    -0.07
    ãĥĥãĤ±
    -0.07
    POSITIVE LOGITS
    uario
    0.06
    uc
    0.06
    Result
    0.06
    ber
    0.06
    ä¸įå®ī
    0.06
    åıĹçIJĨ
    0.06
    Unsigned
    0.06
    ziv
    0.06
    çĿĢæīĭ
    0.06
    éĥ¨åĪĨçļĦ
    0.06
    Activations Density 0.000%

    No Known Activations