© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44799
    Prev
    Next
    INDEX
    Explanations

    battle or fight sequences

    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
    Æ°á»Ľp
    -0.08
    emm
    -0.08
    ила
    -0.08
    é«ĺçħ§
    -0.08
    оÑĩки
    -0.08
    ITY
    -0.07
    usak
    -0.07
    ity
    -0.07
    ariato
    -0.07
    éģĩäºĭ
    -0.07
    POSITIVE LOGITS
    ä¸įæģ¯
    0.09
     waged
    0.08
    ä¸įä¼ij
    0.08
    fight
    0.08
     against
    0.08
    against
    0.08
    Against
    0.07
     melawan
    0.07
     prsa
    0.07
    æ¿ĢçĥĪçļĦ
    0.07
    Activations Density 0.093%

    No Known Activations