© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64130
    Prev
    Next
    INDEX
    Explanations

    review, summarize, think, find

    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
     ÑıкобÑĭ
    -0.07
    ÏĢÏī
    -0.07
    éĻĦè¿ijæľī
    -0.07
     nearby
    -0.07
     arti
    -0.07
    iedere
    -0.07
    antas
    -0.07
    árs
    -0.07
    移
    -0.07
    æĹłéĿŀ
    -0.07
    POSITIVE LOGITS
    æ°´çģ«
    0.07
    èĭŁ
    0.07
    /name
    0.07
    è¿Ļ两个
    0.07
    èĤĩ
    0.06
    游åѦ
    0.06
     bain
    0.06
    quo
    0.06
     ,
    0.06
     Âł
    0.06
    Activations Density 0.006%

    No Known Activations