© 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. 2557
    Prev
    Next
    INDEX
    Explanations

    use instead of

    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
    æĹłèĻij
    -0.08
    åĨįä¹Łä¸į
    -0.08
    æļĩ
    -0.07
    足ä¸įåĩºæĪ·
    -0.07
    ä¸įä¸Ģå®ļæĺ¯
    -0.07
    èĢĮæĹł
    -0.07
    ä¸įåĢ¦
    -0.07
    ãģĿãģĵãģ¾ãģ§
    -0.07
    æľªç»ıæİĪæĿĥ
    -0.07
    足ä¸įåĩº
    -0.07
    POSITIVE LOGITS
    åıĸèĢĮ代ä¹ĭ
    0.15
    代ä¹ĭ
    0.12
     instead
    0.12
    代ãĤıãĤĬãģ«
    0.11
     anzi
    0.10
     Instead
    0.10
    æĽ´æ²¡æľī
    0.10
    Instead
    0.10
    èĢĮæĺ¯
    0.10
    instead
    0.09
    Activations Density 0.301%

    No Known Activations