© 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. 19619
    Prev
    Next
    INDEX
    Explanations

    consider examples or definitions

    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
    éĢı
    -0.08
    .pm
    -0.07
    REAT
    -0.07
    æ¯ıä¸ĢæĿ¡
    -0.07
    æł¸éħ¸æ£Ģæµĭéĺ´æĢ§
    -0.07
    ç»ıå¾Ĺèµ·
    -0.07
    axed
    -0.07
    åĪ°æѤ
    -0.06
    åĪ©
    -0.06
    egal
    -0.06
    POSITIVE LOGITS
    otka
    0.07
    ÙģÙī
    0.07
    [...,
    0.07
     situazioni
    0.07
    yai
    0.07
    åħ³æ³¨åħ¬ä¼Ĺåı·
    0.07
    istik
    0.07
    teman
    0.07
     olyan
    0.07
    omie
    0.07
    Activations Density 0.244%

    No Known Activations