© 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. 10393
    Prev
    Next
    INDEX
    Explanations

    threading and thread exception

    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
    éħį
    -0.07
     malformed
    -0.07
    æĬĺ
    -0.07
    baugh
    -0.06
    åħ´åįİ
    -0.06
     Kot
    -0.06
    illet
    -0.06
    笹
    -0.06
    ży
    -0.06
     putt
    -0.06
    POSITIVE LOGITS
    essus
    0.07
    ä»»æķĻ
    0.07
    less
    0.07
    gable
    0.07
    LOY
    0.07
    ä»İèĢĮ导èĩ´
    0.07
    fulness
    0.07
    Arg
    0.07
    _builtin
    0.06
    clo
    0.06
    Activations Density 0.025%

    No Known Activations