© 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. 38064
    Prev
    Next
    INDEX
    Explanations

    group IV elements

    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¸Ī
    -0.09
    åļı
    -0.08
    gå
    -0.08
    è§Ħ模æľĢ大çļĦ
    -0.08
    vei
    -0.08
    Ñĸм
    -0.07
    åħ¬åı¸è§Ħ模
    -0.07
    stead
    -0.07
     megfelel
    -0.07
    gaard
    -0.07
    POSITIVE LOGITS
    åĬłä¸Ĭ
    0.07
    æĿ¥èĩª
    0.07
    课ä¸Ĭ
    0.07
    浩浩
    0.07
    åİŁå§ĭçļĦ
    0.07
    æĹ¥æĿ¥
    0.07
    天æĢ§
    0.07
     иÑģÑħод
    0.07
    æ¯ı人
    0.07
     Cree
    0.07
    Activations Density 0.001%

    No Known Activations