© 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. 32767
    Prev
    Next
    INDEX
    Explanations

    -substituted chemical names

    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
    andes
    -0.08
    anne
    -0.08
    ocks
    -0.08
    uin
    -0.07
    ullah
    -0.07
    odat
    -0.07
    液çļĦ
    -0.07
    å¹´å¹³åĿĩ
    -0.07
    æľĿ天
    -0.07
    /GPL
    -0.07
    POSITIVE LOGITS
    é«ĺåĪĨ
    0.07
    ä½įç½®çļĦ
    0.07
    âĢij
    0.07
     positions
    0.07
    erne
    0.07
    æĶ¹
    0.07
    ä½įç½®
    0.07
    erner
    0.06
    è·¯éĢı
    0.06
    ç¬Ļ
    0.06
    Activations Density 0.019%

    No Known Activations