© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 29752
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    anh
    -0.07
    sWith
    -0.07
    åĢ¾åIJij
    -0.07
    ading
    -0.07
    ikov
    -0.07
    வà¯ĩ
    -0.07
    ildo
    -0.07
    اÙĨØ´
    -0.06
    edom
    -0.06
    arily
    -0.06
    POSITIVE LOGITS
     MOTOR
    0.07
    åı¯ä»¥æĺ¯
    0.07
     encour
    0.07
    avatars
    0.07
    èĭ±æĸĩåŃĹ
    0.07
     Elm
    0.07
    çĿĽ
    0.07
    avat
    0.07
    abus
    0.07
    quan
    0.06
    Activations Density 0.000%

    No Known Activations