© 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. 38591
    Prev
    Next
    INDEX
    Explanations

    checking correctness

    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
    boro
    -0.07
    éĢļ常æĺ¯
    -0.07
     probably
    -0.06
    æĭĹ
    -0.06
    åIJĦçķĮ
    -0.06
    hia
    -0.06
    ollen
    -0.06
    ¾
    -0.06
    çij
    -0.06
    à¸Ńà¸Ĺ
    -0.06
    POSITIVE LOGITS
    å·²ç»ıå®Įåħ¨
    0.09
    ä»ħä»ħ
    0.09
    æľ¬èº«å°±
    0.09
     ONLY
    0.08
    å·²ç»ıå¾Ī
    0.08
     somehow
    0.08
    ä»ħä»ħæĺ¯
    0.08
     seulement
    0.08
     already
    0.08
    åıªæĺ¯ä¸ºäºĨ
    0.08
    Activations Density 0.022%

    No Known Activations