© 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. 13310
    Prev
    Next
    INDEX
    Explanations

    research and study verbs

    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
    ä»»ä½ķ
    -0.08
    ä»»ä½ķ人
    -0.07
     unless
    -0.06
    æĺİå¹´
    -0.06
    åħ¨ä½ĵ人åijĺ
    -0.06
    è¿ĺæľīä¸Ģç§į
    -0.06
    orem
    -0.06
    éĩĮ
    -0.06
    使æĪij
    -0.06
    ä¸ĢåĪĩ
    -0.06
    POSITIVE LOGITS
     studies
    0.10
     various
    0.09
    缴æİ¥æĪĸ
    0.09
     Various
    0.09
     Ø¥Ùħا
    0.09
    Various
    0.09
    ä¹Łæľīä¸įå°ij
    0.09
     papers
    0.09
    focused
    0.09
    å±Ĥåĩºä¸įç©·
    0.08
    Activations Density 1.852%

    No Known Activations