© 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. 25918
    Prev
    Next
    INDEX
    Explanations

    structure and function

    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
     гаÑģÑĤÑĢи
    -0.08
    æĮŁ
    -0.08
     ваÑĢико
    -0.08
     ÑħолеÑģÑĤе
    -0.08
     ÑĢеквизи
    -0.08
     кви
    -0.08
    éĸ
    -0.08
     Dodatkowo
    -0.08
    èķī
    -0.07
    å¾ģæ±ĤæĦıè§ģ稿
    -0.07
    POSITIVE LOGITS
     âĦĸ
    0.12
    0.10
    âĦĸ
    0.09
     «
    0.09
     âĢŀ
    0.09
     Pavel
    0.08
     Т
    0.08
    .epam
    0.08
     С
    0.08
    н
    0.08
    Activations Density 1.720%

    No Known Activations