© 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. 62214
    Prev
    Next
    INDEX
    Explanations

    is/are/means/has/were/provides/played/occurs

    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
    ynchronously
    -0.07
    -caret
    -0.07
    à¦ĩ
    -0.07
    å°±æĺ¯äºĨ
    -0.07
    á»ģn
    -0.07
    urr
    -0.07
    èĩ³äºİ
    -0.07
    æĤ¨çİ°åľ¨çļĦä½įç½®
    -0.07
    å¾
    -0.07
    odash
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪéľĢè¦ģ
    0.11
    åħ·æľī以ä¸ĭ
    0.10
    é¦ĸåħĪè¦ģ
    0.09
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.09
    主è¦ģæľī
    0.09
    é¦ĸåħĪåľ¨
    0.09
    æľī以ä¸ĭ
    0.09
    以ä¸ĭåĩłä¸ª
    0.09
    é¦ĸåħĪ
    0.08
    以ä¸ĭåĩł
    0.08
    Activations Density 0.521%

    No Known Activations