© 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. 42608
    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
    ocket
    -0.07
    aina
    -0.07
    åĩ¶
    -0.07
    ä»Ģä¹ĪæĥħåĨµ
    -0.07
    åģļåĩºæĿ¥çļĦ
    -0.07
    inite
    -0.07
    让群ä¼Ĺ
    -0.07
    å¾Īæĺİæĺ¾
    -0.06
    mium
    -0.06
    è°IJéŁ³
    -0.06
    POSITIVE LOGITS
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.07
    Violation
    0.06
    个人ç®ĢåİĨ
    0.06
    年审
    0.06
     conditioned
    0.06
    æ³ķåĪĻ
    0.06
    æĥ¹äºº
    0.06
    .freeze
    0.06
    .attr
    0.06
    åįĹä¸ĭ
    0.06
    Activations Density 0.000%

    No Known Activations