© 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. 2721
    Prev
    Next
    INDEX
    Explanations

    structure and arrangements

    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
    ä¸įåĩº
    -0.08
    ilog
    -0.07
    æłĩçļĦ
    -0.07
    èĤļåŃIJ
    -0.07
    handling
    -0.07
    åĩºæ²¡
    -0.07
    åĪ¥
    -0.07
    มูล
    -0.07
    åĪĨåĪ«
    -0.07
    éĢĶ
    -0.07
    POSITIVE LOGITS
    æİĴåĪĹ
    0.13
     arrangement
    0.12
     orderly
    0.10
    /random
    0.09
     structure
    0.09
     organized
    0.09
    æľīåºıçļĦ
    0.08
     rearr
    0.08
    æľīåºı
    0.08
     arrangements
    0.08
    Activations Density 0.014%

    No Known Activations