© 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. 64534
    Prev
    Next
    INDEX
    Explanations

    modal verb followed by a verb

    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
    izas
    -0.08
    ation
    -0.07
    nesc
    -0.07
    irts
    -0.07
     unserem
    -0.07
    åĽłä¸ºæĪij
    -0.07
    让æĪij们ä¸Ģèµ·æĿ¥
    -0.07
    ä¸Ń磩
    -0.07
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.07
    irt
    -0.07
    POSITIVE LOGITS
     oneself
    0.10
    ä½ķåľ°
    0.09
    个æĪĸå¤ļ个
    0.07
    ä¼ļè§īå¾Ĺ
    0.07
    er
    0.07
    thing
    0.07
    ÑģÑĤвом
    0.07
    ERG
    0.07
    -sided
    0.07
    æĪĸå¤ļ个
    0.07
    Activations Density 0.030%

    No Known Activations