© 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. 14963
    Prev
    Next
    INDEX
    Explanations

    books and locations

    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
    zec
    -0.07
    asm
    -0.07
    ziv
    -0.07
    çĿĢä»Ģä¹Ī
    -0.07
    麻çĹ¹
    -0.07
    agar
    -0.07
    atas
    -0.07
    indah
    -0.06
    åĬ¨
    -0.06
    æľīå¿ĥ人
    -0.06
    POSITIVE LOGITS
    çıij
    0.07
    ermann
    0.07
    laut
    0.06
    ä¸ĭåIJĮ
    0.06
    çļĦè§Ħå®ļ
    0.06
    çĪ¾
    0.06
    令第
    0.06
     Lihat
    0.06
     ÑģÑĥпÑĢÑĥгов
    0.06
    plements
    0.06
    Activations Density 0.059%

    No Known Activations