© 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. 58441
    Prev
    Next
    INDEX
    Explanations

    permutation and reordering

    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
    lipse
    -0.08
    ستا
    -0.07
    repid
    -0.07
    cian
    -0.07
    åĪ·
    -0.07
    Formats
    -0.07
    estre
    -0.07
    .Generation
    -0.07
    ä¹Łä¸įæķ¢
    -0.07
    .Generated
    -0.07
    POSITIVE LOGITS
    æİĴåĪĹ
    0.09
     permutation
    0.09
    Ĭ
    0.09
    è°ĥæį¢
    0.08
     reorder
    0.08
     rearr
    0.08
     order
    0.08
    atcher
    0.08
     symmetry
    0.08
     reordered
    0.08
    Activations Density 0.009%

    No Known Activations