© 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. 56377
    Prev
    Next
    INDEX
    Explanations

    etymology from Latin Greek

    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
    otis
    -0.09
    sdale
    -0.09
     GENERATED
    -0.08
    æľ¬æĸĩ为åįļ主
    -0.08
    .lazy
    -0.08
    nement
    -0.08
    -Bar
    -0.08
    åıĭæĥħéĵ¾æİ¥
    -0.08
    hra
    -0.08
    ffit
    -0.08
    POSITIVE LOGITS
     '
    0.07
     "
    0.07
     meaning
    0.06
    :
    0.06
     conver
    0.06
    æĦıæĢĿæĺ¯
    0.05
     sh
    0.05
     w
    0.05
    ↵↵
    0.05
    ools
    0.05
    Activations Density 0.067%

    No Known Activations