© 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. 24759
    Prev
    Next
    INDEX
    Explanations

    nor, neither, or constructions

    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
     nonetheless
    -0.08
    ?action
    -0.08
    åı¦å¤ĸè¿ĺæľī
    -0.08
    ehu
    -0.07
     sucker
    -0.07
     justamente
    -0.07
    ä¸įèĭŁ
    -0.07
    ä¸įä¸Ģæł·çļĦ
    -0.07
    ä¸įä¸Ģæł·
    -0.07
    ystone
    -0.07
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.17
     nor
    0.15
     tampoco
    0.15
     whatsoever
    0.13
     anything
    0.13
    ä»»ä½ķ
    0.13
    æıIJä¾Ľä»»ä½ķ
    0.13
    åģļä»»ä½ķ
    0.12
    ä»»ä½ķå½¢å¼ıçļĦ
    0.12
     siquiera
    0.12
    Activations Density 0.198%

    No Known Activations