© 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. 7783
    Prev
    Next
    INDEX
    Explanations

    every, amount, single, entirely

    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
    à¹Ģหล
    -0.08
    ä¾µçĬ¯æĤ¨çļĦ
    -0.07
     misd
    -0.07
    åĪĨæķ£
    -0.07
    ocre
    -0.07
    å°ijäºİ
    -0.07
    মান
    -0.07
    æľīæĦı
    -0.07
    رÙĥاÙĨ
    -0.07
    çªľ
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĪĩçļĦ
    0.09
    ä¸įåħį
    0.09
    åĩ¡äºĭ
    0.09
    éļ¾åħį
    0.09
     indiscrim
    0.08
    å°ĨæīĢæľī
    0.08
    æĺ¯ä¸įåı¯èĥ½çļĦ
    0.08
     everywhere
    0.08
    /all
    0.08
    åľ¨æīĢæľī
    0.08
    Activations Density 0.048%

    No Known Activations