© 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. 4058
    Prev
    Next
    INDEX
    Explanations

    sigma-algebra

    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
     arro
    -0.07
    ä¸ĭåĿ¡
    -0.07
    溪éķĩ
    -0.07
    æĻ¶ä½ĵ
    -0.07
     unsupported
    -0.07
    boro
    -0.07
    unsupported
    -0.07
    _argv
    -0.07
    ä¸įçĿĢ
    -0.07
    جاÙĩ
    -0.07
    POSITIVE LOGITS
    管è¾ĸ
    0.09
    çī¹è®¸
    0.08
    ä¸ĢéĢļ
    0.08
    æķ²éŨ
    0.08
    è¦ĨçĽĸ
    0.08
     finest
    0.07
    iance
    0.07
     Cover
    0.07
    è¦ĨçĽĸäºĨ
    0.07
    ediat
    0.07
    Activations Density 0.008%

    No Known Activations