© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17621
    Prev
    Next
    INDEX
    Explanations

    following "on"

    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
    icter
    -0.07
    inata
    -0.06
    enko
    -0.06
    ä¸įä¼ļ对
    -0.06
    ero
    -0.06
    arcy
    -0.06
    atin
    -0.06
    ledge
    -0.06
     behind
    -0.06
    izards
    -0.06
    POSITIVE LOGITS
    /from
    0.11
     behalf
    0.09
    åĴĮå½±åĵį
    0.09
     each
    0.08
    æ¯ıä¸Ģ个è§ĴèIJ½
    0.08
    bbing
    0.08
    åħ¨ä½ĵåѦçĶŁ
    0.07
    æ¯ıä¸Ģ个
    0.07
    æ¯ıä¸ĢæĿ¡
    0.07
    popover
    0.07
    Activations Density 0.151%

    No Known Activations