© 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. 34541
    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
    oba
    -0.07
    aba
    -0.07
    aban
    -0.07
    ook
    -0.07
    oose
    -0.07
    atin
    -0.07
    umbre
    -0.07
    æľīéĻIJ责任åħ¬åı¸
    -0.07
    emade
    -0.07
    ä¸Ń天
    -0.07
    POSITIVE LOGITS
    æĪĸä¸į
    0.07
    .Abstract
    0.07
    æĺķ
    0.07
    çIJĨå·¥åѦéĻ¢
    0.07
     quals
    0.06
    ש×ķ
    0.06
    gments
    0.06
    valu
    0.06
    ìħĶ
    0.06
    ]|[
    0.06
    Activations Density 0.000%

    No Known Activations