© 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. 16424
    Prev
    Next
    INDEX
    Explanations

    yes/no questions

    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
    æĭĽ
    -0.08
    å¤©çľ¼æŁ¥
    -0.07
    undry
    -0.07
    çĶ¨æ°´éĩı
    -0.07
    /download
    -0.07
    æű
    -0.06
    ijen
    -0.06
    Statistics
    -0.06
    _unused
    -0.06
    _runner
    -0.06
    POSITIVE LOGITS
     Incorrect
    0.08
    /false
    0.08
     negatively
    0.08
     affirmative
    0.08
    æŃ£ç¡®çļĦæĺ¯
    0.08
    åIJ¦å®ļ
    0.08
     correct
    0.08
     phủ
    0.07
     correctness
    0.07
    åıįä¹īè¯į
    0.07
    Activations Density 0.010%

    No Known Activations