© 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. 43753
    Prev
    Next
    INDEX
    Explanations

    scientific terms and notation

    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
    æľīçļĦæĺ¯
    -0.06
    wany
    -0.06
    ksom
    -0.06
    涤
    -0.06
    è¿IJåĬ¨çļĦ
    -0.06
    æĭ¥
    -0.06
    kis
    -0.06
    注å®ļ
    -0.06
    è¶Ĭ
    -0.06
    nist
    -0.05
    POSITIVE LOGITS
     (`
    0.10
    åį³
    0.08
    å°ıå®Ŀ
    0.08
     (:
    0.08
     ($
    0.08
     (^
    0.08
     (\
    0.08
     (++
    0.08
     tức
    0.08
     ((__
    0.08
    Activations Density 0.092%

    No Known Activations