© 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. 38604
    Prev
    Next
    INDEX
    Explanations

    battle of

    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
    è¿Ļç§įçݰ象
    -0.07
     Titanic
    -0.07
    éĴĵ
    -0.07
     prostit
    -0.07
    åħ¨çIJĥåĮĸ
    -0.06
     skyrocket
    -0.06
    ä½ĵè´´
    -0.06
    etect
    -0.06
    ç´§å¯Ĩ
    -0.06
    大æĬĬ
    -0.06
    POSITIVE LOGITS
     contre
    0.10
    contre
    0.09
     against
    0.09
     engagements
    0.09
     победÑĭ
    0.09
    against
    0.09
     пÑĢоÑĤив
    0.09
     rematch
    0.09
     victory
    0.09
     victories
    0.09
    Activations Density 0.213%

    No Known Activations