© 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. 15326
    Prev
    Next
    INDEX
    Explanations

    error or 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
    EDGE
    -0.08
    .NewReader
    -0.08
    ì§Ŀ
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.07
    plies
    -0.07
    æīĭæľºç«Ļ
    -0.07
    reuse
    -0.07
    UDI
    -0.07
    uide
    -0.07
    DTV
    -0.07
    POSITIVE LOGITS
     unfore
    0.11
     unexpected
    0.10
     occurred
    0.09
    unexpected
    0.08
     inesper
    0.08
     caused
    0.08
    çĻºçĶŁ
    0.07
    Unexpected
    0.07
     occured
    0.07
     unexpectedly
    0.07
    Activations Density 0.168%

    No Known Activations