© 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. 16421
    Prev
    Next
    INDEX
    Explanations

    names and affiliations

    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
    åij¨æŁIJ
    -0.07
    ingin
    -0.07
    ä¸ĬéŨ
    -0.06
    etar
    -0.06
    äºĶ彩缤纷
    -0.06
    æķĻèĤ²è¡ĮæĶ¿éĥ¨éŨ
    -0.06
    ä¸ĬéŨæľįåĬ¡
    -0.06
    insk
    -0.06
    Ñļ
    -0.06
     Neutral
    -0.06
    POSITIVE LOGITS
    æīĢåľ¨åįķä½į
    0.08
     gradu
    0.07
     firstname
    0.07
    .mi
    0.07
    éķIJ
    0.07
    è¿ĶåĽŀåĪĹ表
    0.07
     corresp
    0.07
    borg
    0.07
     ebenfalls
    0.07
    ä»Ģä¹Īåij¢
    0.07
    Activations Density 0.718%

    No Known Activations