© 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. 41479
    Prev
    Next
    INDEX
    Explanations

    numbers in brackets

    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
    æĦģ
    -0.07
    离岸
    -0.07
    æļ¦
    -0.07
    OLER
    -0.06
    elsey
    -0.06
    å¥Ĺ
    -0.06
    chung
    -0.06
    好åĥıåľ¨
    -0.06
    estra
    -0.06
    cing
    -0.06
    POSITIVE LOGITS
    вига
    0.08
    çļĦæŶåĢĻäºĨ
    0.07
    ẻ
    0.07
    isah
    0.07
    eah
    0.07
    oÅĤ
    0.07
    å·²ä¸İ
    0.07
    wid
    0.06
     вÑĭÑģÑĤÑĥплениÑı
    0.06
    oja
    0.06
    Activations Density 0.056%

    No Known Activations