© 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. 11730
    Prev
    Next
    INDEX
    Explanations

    ABLE, RC, 2, review, Background, arge

    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
    æķĻèĤ²ä¸Ńå¿ĥ
    -0.07
    Ùĩد
    -0.06
    guas
    -0.06
    ר×ķת
    -0.06
     пÑĢиÑĩ
    -0.06
    ç£ģ
    -0.06
    æĦĪ
    -0.06
    ykk
    -0.06
    ı
    -0.06
    ez
    -0.06
    POSITIVE LOGITS
    ibat
    0.08
    ="__
    0.07
    ())[
    0.07
    )[:
    0.07
    ()][
    0.07
    çļĦ人è¿ĺ
    0.07
    nado
    0.07
    _UTF
    0.07
    eloos
    0.07
    erno
    0.07
    Activations Density 0.028%

    No Known Activations