© 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. 45210
    Prev
    Next
    INDEX
    Explanations

    first node initialization

    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
    ä¹Łä¸įå¤ļ
    -0.08
    anaf
    -0.07
    .*(
    -0.07
     verschw
    -0.07
    éĢĨæµģ
    -0.07
     Postado
    -0.07
    neos
    -0.07
    alse
    -0.07
    ä¸Ĭé£İ
    -0.07
    eed
    -0.06
    POSITIVE LOGITS
    ãĥĶãĥ³
    0.08
    пин
    0.07
    æĹ¢åı¯ä»¥
    0.07
    аÑĤÑĭ
    0.07
    ppy
    0.07
    éĴ¦
    0.07
    à¹Į
    0.07
    ç»Ńè´¹
    0.06
    uin
    0.06
     newNode
    0.06
    Activations Density 0.036%

    No Known Activations