© 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. 65171
    Prev
    Next
    INDEX
    Explanations

    American film noir thriller

    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
    èĥ¡éĶ¦æ¶Ľ
    -0.09
    亿欧åħĥ
    -0.09
     Serang
    -0.09
    æ¬§çĽŁ
    -0.09
    奥巴马
    -0.08
    ä¸ĩ欧åħĥ
    -0.08
    èģª
    -0.08
     Zhao
    -0.08
    amana
    -0.07
    绣é¢Ĩ
    -0.07
    POSITIVE LOGITS
     Soviet
    0.11
     USSR
    0.11
    æĸĩéĿ©
    0.11
     Ð¡Ð¡Ð¡Ðł
    0.10
     Yugosl
    0.10
     ÑģовеÑĤ
    0.10
     Yugoslavia
    0.10
    èĭıèģĶ
    0.10
     RCA
    0.10
     Eisenhower
    0.10
    Activations Density 1.345%

    No Known Activations