© 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. 41027
    Prev
    Next
    INDEX
    Explanations

    actions and outcomes

    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
    ä¸ĭåIJĮ
    -0.08
     jij
    -0.07
    ä¸įæĽ¾
    -0.07
    åıĪãģ¯
    -0.07
    ãģĦãģļãĤĮ
    -0.06
    çļĦç¼ĺæķħ
    -0.06
    æľīæĦŁ
    -0.06
     appunto
    -0.06
    çļĨåı¯
    -0.06
    åĴ
    -0.06
    POSITIVE LOGITS
    æĸ¹éĿ¢ä¹Ł
    0.13
    åĪĻè¦ģ
    0.12
    æĸ¹éĿ¢
    0.12
    åĪĻæĺ¯
    0.12
    åĪĻéľĢè¦ģ
    0.11
    åĪĻ以
    0.10
    åĪĻä¼ļ
    0.10
    åĪĻåı¯ä»¥
    0.10
    åĪĻçĶ±
    0.10
    åĪĻ
    0.10
    Activations Density 0.013%

    No Known Activations