© 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. 45249
    Prev
    Next
    INDEX
    Explanations

    examples, snippets, illustrative parts

    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
    algo
    -0.08
    eron
    -0.08
    æľ¬çīĪ
    -0.08
    inaldo
    -0.07
    berger
    -0.07
    arz
    -0.07
    åħ¨éĿł
    -0.07
    storybook
    -0.07
    æľ¬ç«ĻæīĢæľī
    -0.07
    åħ¨éķĩ
    -0.07
    POSITIVE LOGITS
     representative
    0.11
     exemplary
    0.09
     snippet
    0.09
     snippets
    0.09
     exempl
    0.09
    代表æĢ§çļĦ
    0.09
    示ä¾ĭ
    0.09
     examples
    0.09
    代表æĢ§
    0.09
    ä¸Ģæĸij
    0.08
    Activations Density 0.181%

    No Known Activations