© 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. 65219
    Prev
    Next
    INDEX
    Explanations

    SELECT, example, join

    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
    weeney
    -0.07
    é¾Ļæ¹¾
    -0.07
    è¯Ļ
    -0.07
    à°ªà±ģ
    -0.07
    olson
    -0.07
    vus
    -0.07
     incumbent
    -0.07
    ä¸Ģè§ī
    -0.06
    ugel
    -0.06
    etty
    -0.06
    POSITIVE LOGITS
    ä¾ĭå¦Ĥ
    0.25
    æ¯Ķå¦Ĥ
    0.20
     ÐĿапÑĢимеÑĢ
    0.20
     напÑĢимеÑĢ
    0.19
    æ¯Ķå¦Ĥ说
    0.18
    ä¾ĭ
    0.18
    ä¾ĭãģĪãģ°
    0.17
     ìĺĪ를
    0.17
    напÑĢимеÑĢ
    0.17
     example
    0.17
    Activations Density 0.829%

    No Known Activations