© 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. 21119
    Prev
    Next
    INDEX
    Explanations

    block or expressed

    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
    onar
    -0.09
    erah
    -0.08
    æĪĸèĢħæĺ¯
    -0.08
    orer
    -0.08
    Æ°á»Łng
    -0.07
     addirittura
    -0.07
    orm
    -0.07
    æĪĸæĺ¯
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    æĸ¹æŃ£
    -0.07
    POSITIVE LOGITS
    ä¸Ķ
    0.08
    ä¸Ķåħ·æľī
    0.08
    ä¸Ķæľī
    0.07
    ä¸Ķåľ¨
    0.07
    cesi
    0.06
    aval
    0.06
     but
    0.06
    plib
    0.06
     obviously
    0.06
    zl
    0.06
    Activations Density 0.016%

    No Known Activations