© 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. 25412
    Prev
    Next
    INDEX
    Explanations

    smallest 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
    éļıæīĭ
    -0.08
    èĩªå·±éĥ½
    -0.08
    æ·ĺæ±°
    -0.07
    é¡į
    -0.07
    溢
    -0.07
    werkt
    -0.07
    åıij表
    -0.07
     Ahead
    -0.07
    ombo
    -0.07
    åĪĨç»Ħ
    -0.07
    POSITIVE LOGITS
    æ£ł
    0.08
     Schwartz
    0.08
    utr
    0.07
     UIL
    0.07
    å°½åı¯èĥ½çļĦ
    0.07
    以æľĢ
    0.07
     tron
    0.07
    壹
    0.07
    ä¸İæĿİ
    0.07
    ächst
    0.07
    Activations Density 0.034%

    No Known Activations