© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14834
    Prev
    Next
    INDEX
    Explanations

    channel subsystem, management, class, lengths

    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
    ep
    -0.07
    uno
    -0.07
    иÑĩ
    -0.07
    åħ³å¤´
    -0.07
    常å§Ķä¼ļ
    -0.07
    angler
    -0.07
     darn
    -0.07
    åľºåIJĪ
    -0.07
    ânia
    -0.06
    anders
    -0.06
    POSITIVE LOGITS
    à§įড
    0.11
    HandlerContext
    0.11
    odox
    0.10
    sterol
    0.10
    rift
    0.10
    witz
    0.10
    opathy
    0.09
    überg
    0.09
    zinho
    0.09
    ä¸įçķħ
    0.09
    Activations Density 0.021%

    No Known Activations