© 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. 51012
    Prev
    Next
    INDEX
    Explanations

    player selection

    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
    伺
    -0.08
    .writeln
    -0.07
    äºİè¡Į
    -0.07
    ibun
    -0.07
    ception
    -0.07
    éĢļè¿ĩå°Ĩ
    -0.06
    epe
    -0.06
    bourne
    -0.06
    eper
    -0.06
    æĸ½è¡Į
    -0.06
    POSITIVE LOGITS
     selected
    0.13
     selection
    0.11
    éĢīä¸Ń
    0.11
    selected
    0.11
     selections
    0.11
    ç»ĦåIJĪ
    0.11
    åħ¨éĢī
    0.10
     select
    0.10
    éĢīèĩª
    0.10
    çļĦç»ĦåIJĪ
    0.10
    Activations Density 0.037%

    No Known Activations