© 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. 16117
    Prev
    Next
    INDEX
    Explanations

    numbers like three, four, five

    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
    åĩłçĤ¹
    -0.08
    å½ĵ头
    -0.08
    γκ
    -0.08
    वर
    -0.08
    lend
    -0.07
    è¯Ŀ说
    -0.07
    é¾ĻèĻİ
    -0.07
     Entire
    -0.07
    icast
    -0.07
    åĩłå¤§
    -0.07
    POSITIVE LOGITS
     distinct
    0.10
     mutually
    0.10
     ìĦľë¡ľ
    0.08
    äºĴ缸
    0.08
    åIJĦåħ·
    0.08
    ä¹ĭå¤ļ
    0.08
    (!
    0.08
    ãģ¤ãģ®
    0.08
    åıĬ以ä¸Ĭ
    0.08
     ê°ľìĿĺ
    0.08
    Activations Density 0.272%

    No Known Activations