© 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. 65112
    Prev
    Next
    INDEX
    Explanations

    patent or legal document citations

    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
    ä¸įçĶ¨
    -0.06
    '
    -0.06
    .utc
    -0.06
    ä¸ľå±±
    -0.05
    æºľ
    -0.05
    æĤ£
    -0.05
    ro
    -0.05
    ä¸Ģ
    -0.05
    2
    -0.05
    å¿«æĦŁ
    -0.05
    POSITIVE LOGITS
    åı·æĸĩ件
    0.09
    лÑĮки
    0.09
    请åħ³æ³¨
    0.09
    THR
    0.09
    bish
    0.09
     há»ĵn
    0.09
    äºijé£ŀ
    0.08
    ä¸īçķĮ
    0.08
    udget
    0.08
    第ä¸Ģåįĥ
    0.08
    Activations Density 0.469%

    No Known Activations