© 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. 12101
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    ÑģÑĤвий
    -0.08
    serter
    -0.08
    vertiser
    -0.08
    cliffe
    -0.08
     filet
    -0.07
    sembler
    -0.07
    æµİ
    -0.07
    eded
    -0.07
    achel
    -0.07
    entifier
    -0.07
    POSITIVE LOGITS
    ucho
    0.06
    ulah
    0.06
    abh
    0.06
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.06
    ka
    0.06
    æľīåħ³çļĦ
    0.06
    IBA
    0.06
    ax
    0.06
    ä¹ĭå¤ľ
    0.06
    мÑı
    0.06
    Activations Density 2.082%

    No Known Activations