© 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. 27778
    Prev
    Next
    INDEX
    Explanations

    legal contexts: plaintiff, defendant, appellee

    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
    å°±æĺ¯æľĢ好çļĦ
    -0.09
    å°±æĺ¯ä¸į
    -0.08
    ãĤĤãģ®ãģ¯
    -0.07
    aner
    -0.07
    .sax
    -0.07
    ä¿±è¿Ľ
    -0.07
    ANY
    -0.07
    outh
    -0.07
    гно
    -0.07
    UCK
    -0.07
    POSITIVE LOGITS
    .asm
    0.08
    enta
    0.07
    etta
    0.07
    çļĦä¸Ģéĥ¨åĪĨ
    0.07
     provider
    0.06
    imed
    0.06
    à¸Ĥัà¹īà¸Ļ
    0.06
    æŁIJç§į
    0.06
    çľĭå¾ħ
    0.06
    ared
    0.06
    Activations Density 0.128%

    No Known Activations