© 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. 13876
    Prev
    Next
    INDEX
    Explanations

    formula syntax

    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
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
     Taip
    -0.07
    #w
    -0.07
    /tty
    -0.07
    êµī
    -0.07
    åħ¬åı¸èį£èªī
    -0.07
    åıªä»£è¡¨
    -0.07
    /manual
    -0.07
    <typeof
    -0.07
     Olah
    -0.07
    POSITIVE LOGITS
    æĺ¯ä»Ģä¹Īæł·çļĦ
    0.07
     âĢ¦
    0.07
     wherein
    0.07
    aturing
    0.07
    estyle
    0.06
    å°±æĽ¾
    0.06
    ä»Ģä¹ĪæĦıæĢĿ
    0.06
    ={(
    0.06
    kos
    0.06
    opedia
    0.06
    Activations Density 0.115%

    No Known Activations