© 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. 47735
    Prev
    Next
    INDEX
    Explanations

    who died, what year, what country

    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
    éľĨ
    -0.07
    åı¸ç©º
    -0.06
    etic
    -0.06
    æĺ¯æľĢ好çļĦ
    -0.06
    bin
    -0.06
     schematic
    -0.06
    çļĦå¿ĥå¾Ĺ
    -0.06
    imeo
    -0.06
    æ¦Ĥ念çļĦ
    -0.06
    ä½İæ²ī
    -0.06
    POSITIVE LOGITS
     famously
    0.09
    obot
    0.08
    иÑģÑĤÑĢа
    0.08
     trivia
    0.08
     inaugur
    0.08
    edal
    0.08
     famous
    0.08
     Compon
    0.08
    èĭ±æĸĩåIJį称
    0.08
    -Origin
    0.07
    Activations Density 0.154%

    No Known Activations