© 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. 50350
    Prev
    Next
    INDEX
    Explanations

    variables followed by punctuation

    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
    _MINOR
    -0.08
    å°ıèıľ
    -0.08
    ersist
    -0.08
    éļ¾ä»¥å¿ĺæĢĢ
    -0.07
    å¾·åŁº
    -0.07
     Toro
    -0.07
    ä»ĸä¹Łæĺ¯
    -0.07
    rowse
    -0.07
    è¿Ļ个æĸ¹æ³ķ
    -0.07
    _LOOK
    -0.07
    POSITIVE LOGITS
    aza
    0.07
     -
    0.06
    azo
    0.06
     Co
    0.06
     co
    0.06
    åĸľæ¬¢ä½ł
    0.06
    abo
    0.06
     зв
    0.05
    ä¸īåĪĨ
    0.05
     evangel
    0.05
    Activations Density 0.019%

    No Known Activations