© 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. 2347
    Prev
    Next
    INDEX
    Explanations

    \frac and rewrite

    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
    borg
    -0.08
    alda
    -0.07
    naver
    -0.07
    паÑĤÑĮ
    -0.07
    tur
    -0.07
     yl
    -0.07
    ture
    -0.07
    nor
    -0.07
    allo
    -0.07
    rane
    -0.07
    POSITIVE LOGITS
    RAF
    0.07
    -render
    0.06
    лам
    0.06
     Federation
    0.06
     بد
    0.06
     rewrite
    0.06
     diag
    0.06
    åĽºå®ļ
    0.06
    æĿŁ
    0.06
    ocas
    0.06
    Activations Density 0.006%

    No Known Activations