© 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. 46044
    Prev
    Next
    INDEX
    Explanations

    examples of translations

    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
    ìłĦìĿĺ
    -0.07
    ipas
    -0.07
    åĵªå®¶
    -0.07
    stÄĻp
    -0.07
     -.
    -0.07
     '.
    -0.07
    &utm
    -0.07
    åŃĺåľ¨ä¸Ģå®ļçļĦ
    -0.06
    缸åIJĮçļĦ
    -0.06
    irl
    -0.06
    POSITIVE LOGITS
     például
    0.13
     bijvoorbeeld
    0.12
     beispielsweise
    0.11
    尤为
    0.11
     misalnya
    0.11
     particularly
    0.10
    éĻ¤å¤ĸ
    0.10
     ÙħØ«ÙĦا
    0.10
     Particularly
    0.09
     напÑĢимеÑĢ
    0.09
    Activations Density 1.144%

    No Known Activations