© 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. 43218
    Prev
    Next
    INDEX
    Explanations

    cyclic structures and integers

    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
    reeNode
    -0.08
    /MIT
    -0.07
    aram
    -0.07
     karenanya
    -0.07
    ipasi
    -0.07
    [__
    -0.07
    ENTES
    -0.07
    chst
    -0.07
    ç«Ļä¸Ĭ
    -0.07
    å±±åı£
    -0.07
    POSITIVE LOGITS
     sufficiently
    0.09
    æľīè¶³å¤ŁçļĦ
    0.08
    èĩ³å°ij
    0.07
     suffisamment
    0.07
    owski
    0.07
    并ä¸Ķåľ¨
    0.07
    并ä¸Ķ
    0.07
     AND
    0.07
     preferably
    0.07
    è¶³å¤Ł
    0.07
    Activations Density 0.007%

    No Known Activations