© 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. 21083
    Prev
    Next
    INDEX
    Explanations

    programming input and view access

    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
    æī¿æĭħçļĦ
    -0.08
    aina
    -0.07
    åĩºåİ»çļĦ
    -0.07
    ĺIJ
    -0.07
    ndon
    -0.07
    /functions
    -0.06
    engel
    -0.06
    æī¿æĭħçĿĢ
    -0.06
    ASON
    -0.06
    å¼Ģå±ķçļĦ
    -0.06
    POSITIVE LOGITS
    otron
    0.08
    adÄĽ
    0.08
    ufer
    0.08
    _into
    0.08
    outu
    0.07
    chè
    0.07
    iming
    0.07
    intos
    0.07
    Õ¿
    0.07
    llu
    0.07
    Activations Density 0.003%

    No Known Activations