© 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. 29279
    Prev
    Next
    INDEX
    Explanations

    presenting a description or overview

    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
    erein
    -0.08
     foregoing
    -0.08
    对ä¸Ĭè¿°
    -0.07
    ä¸Ĭè¿°
    -0.07
    icul
    -0.07
    åIJİèĢħ
    -0.07
    åľ¨ä¸Ĭè¿°
    -0.06
    é£İåIJ¹
    -0.06
    amma
    -0.06
     above
    -0.06
    POSITIVE LOGITS
    æĹ¢èĥ½
    0.09
    å®ļçķª
    0.08
    à¹ĥหà¹īà¹Ģหà¹ĩà¸Ļ
    0.08
    åĩłä¸ªæĸ¹éĿ¢
    0.08
    æĹ¢çĦ¶æĺ¯
    0.08
     íģ¬ê²Į
    0.08
     outlining
    0.08
    åĭ¾åĭĴåĩº
    0.08
    ä¸Ģæĺ¯è¦ģ
    0.08
    æľĢèĥ½
    0.08
    Activations Density 0.004%

    No Known Activations