© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17701
    Prev
    Next
    INDEX
    Explanations

    math formatting characters

    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
    à§ĩ
    -0.10
    erweise
    -0.10
    iÅĤ
    -0.09
    ÙĬ
    -0.09
    i
    -0.08
    ÑģÑĮ
    -0.08
    à¯į
    -0.08
    ļ
    -0.08
    çļĦå°±æĺ¯
    -0.07
     niá»ĩm
    -0.07
    POSITIVE LOGITS
    Ø©
    0.11
    ãĤĪãģĨãģª
    0.11
    ãĥ£
    0.10
    es
    0.10
    ä½Ĩä¸įéĻIJäºİ
    0.10
    eh
    0.08
    ãĤĪãģĨãģ«
    0.08
    eval
    0.08
    ãĢģãĢİ
    0.08
    /'
    0.08
    Activations Density 0.080%

    No Known Activations