© 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. 9872
    Prev
    Next
    INDEX
    Explanations

    those that

    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
     himself
    -0.17
     koji
    -0.14
     Ñıкий
    -0.13
     sÄĥu
    -0.13
     коÑĤоÑĢÑĭй
    -0.13
     коÑĺи
    -0.13
     nostru
    -0.12
     Himself
    -0.12
     ktorý
    -0.11
     který
    -0.11
    POSITIVE LOGITS
     herself
    0.19
     koju
    0.17
     koja
    0.16
     коÑĺа
    0.16
     коÑĤоÑĢаÑı
    0.15
     коÑĤоÑĢÑĥÑİ
    0.14
     हà¥ĭतà¥Ģ
    0.14
     kojoj
    0.13
     która
    0.13
     коÑıÑĤо
    0.12
    Activations Density 0.896%

    No Known Activations