© 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. 9674
    Prev
    Next
    INDEX
    Explanations

    understanding and communication

    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
    èĢĺ
    -0.08
    ubu
    -0.07
    空åīį
    -0.07
    ilon
    -0.07
    룬
    -0.07
    aber
    -0.07
    uve
    -0.07
    rud
    -0.07
    기ìŀIJ
    -0.06
     باÙĦØ°Ùĥر
    -0.06
    POSITIVE LOGITS
    è°ģæĺ¯
    0.10
    ä½ķ为
    0.09
    æ¸ħæ¸ħæ¥ļæ¥ļ
    0.09
    èĩªå·±æĺ¯
    0.08
    ä»Ģä¹Īæĺ¯
    0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    0.08
    稿件æĿ¥æºIJ
    0.07
    edian
    0.07
    åĴĮæī§è¡Į
    0.07
    _modules
    0.07
    Activations Density 0.564%

    No Known Activations