© 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. 57514
    Prev
    Next
    INDEX
    Explanations

    matrices average kernel size

    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
    asia
    -0.08
    为人
    -0.07
    reb
    -0.07
    赶ä¸Ĭ
    -0.07
    ´
    -0.07
    öld
    -0.07
    hton
    -0.07
    åħį
    -0.07
    .removeChild
    -0.07
    ÑĩеÑĤа
    -0.07
    POSITIVE LOGITS
    bot
    0.07
    _attrs
    0.06
    ä¾Ŀæ³ķ追究责任
    0.06
    çħ
    0.06
    樽
    0.06
     doomed
    0.06
    ä¸Ńæī¾åĪ°
    0.06
     Conse
    0.06
    unki
    0.06
    ç§įç§į
    0.06
    Activations Density 0.001%

    No Known Activations