© 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. 3604
    Prev
    Next
    INDEX
    Explanations

    exceptions

    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
    iles
    -0.08
    iddy
    -0.07
     either
    -0.07
    IID
    -0.07
    è¦ģä¹Ī
    -0.07
    iger
    -0.07
    è¦ģçļĦ
    -0.07
    Å¡Äį
    -0.07
    uez
    -0.06
    大路
    -0.06
    POSITIVE LOGITS
     exceptions
    0.12
     Exceptions
    0.12
    ä¾ĭå¤ĸ
    0.11
    exceptions
    0.11
    æľīæŶåĢĻ
    0.10
     exception
    0.10
    Exceptions
    0.10
    ä¸įèĥ½å®Įåħ¨
    0.09
     sometimes
    0.09
    åľ¨æŁIJäºĽ
    0.09
    Activations Density 0.025%

    No Known Activations