© 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. 64924
    Prev
    Next
    INDEX
    Explanations

    знак

    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
     herself
    -0.13
     हà¥ĭतà¥Ģ
    -0.11
     коÑĺа
    -0.11
     थà¥Ģ
    -0.11
     koja
    -0.10
     kojoj
    -0.10
     koju
    -0.10
     हà¥ĭà¤Ĺ
    -0.10
     Ñıка
    -0.09
     ÙĨÙģسÙĩا
    -0.09
    POSITIVE LOGITS
     himself
    0.16
    æĪĸå¤ļ个
    0.14
     sÄĥu
    0.13
     nostru
    0.12
     коÑĤоÑĢÑĭй
    0.11
     Himself
    0.11
    åĴĮä»ĸçļĦ
    0.10
     οÏĢοίο
    0.10
     koji
    0.10
     Ñıкий
    0.10
    Activations Density 0.092%

    No Known Activations