© 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. 51287
    Prev
    Next
    INDEX
    Explanations

    series or category

    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
    åı¯åľ¨
    -0.09
    åı¯æľīæķĪ
    -0.08
    åı¯éĢīæĭ©
    -0.08
    è¿ĺåı¯
    -0.07
    åħ¨è¿ĩç¨ĭ
    -0.07
    acent
    -0.07
    çªģçł´
    -0.07
    aban
    -0.07
    åı¯åĪĨ为
    -0.07
    åı¯éĢļè¿ĩ
    -0.07
    POSITIVE LOGITS
    éĤ£æĺ¯ä¸Ģ个
    0.08
    usted
    0.07
    leden
    0.07
    emun
    0.07
    åĩºçĶŁçļĦ
    0.07
    åĴĮæĶ¹è¿Ľ
    0.07
    ä¸įå¼ĥ
    0.07
    <\/
    0.07
    ##_
    0.07
    ogie
    0.07
    Activations Density 0.008%

    No Known Activations