© 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. 23973
    Prev
    Next
    INDEX
    Explanations

    .lo files

    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
     Bola
    -0.07
    ood
    -0.07
    ã
    -0.07
    æĥħ
    -0.07
    ony
    -0.07
    oni
    -0.07
    benh
    -0.07
    并å¤Ħ
    -0.06
    è¦ģèµ°
    -0.06
     ((_
    -0.06
    POSITIVE LOGITS
    ango
    0.09
    çļĦæľĢåIJİ
    0.08
    æľĢåIJİçļĦ
    0.08
    æľĢåIJİæĺ¯
    0.08
    ewire
    0.08
     наконеÑĨ
    0.08
    erva
    0.08
    สุà¸Ķà¸Ĺà¹īาย
    0.08
    arrer
    0.07
    idet
    0.07
    Activations Density 0.079%

    No Known Activations