© 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. 33668
    Prev
    Next
    INDEX
    Explanations

    winner, loser, first, highest, late, whoever

    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
    åĤ¨
    -0.08
    个人è¡Į为
    -0.08
    åĸľéĹ»
    -0.07
    .std
    -0.07
     reserv
    -0.07
    eras
    -0.07
    严äºİ
    -0.06
    armi
    -0.06
    ä»»ä½ł
    -0.06
    åĴĮå¤ĸ
    -0.06
    POSITIVE LOGITS
     whoever
    0.10
    è°ģæĺ¯
    0.10
    è°ģ
    0.09
    winner
    0.09
     Whoever
    0.09
    æĺ¯è°ģ
    0.09
     winner
    0.09
     who
    0.09
    æĬ¢åħĪ
    0.09
    çļĦä¸Ģæĸ¹
    0.08
    Activations Density 0.072%

    No Known Activations