© 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. 47239
    Prev
    Next
    INDEX
    Explanations

    rely on

    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
    Õ¡Öģ
    -0.09
    eningen
    -0.08
    ầm
    -0.08
    egral
    -0.08
    tenham
    -0.08
    cipt
    -0.08
    åıįä¹ĭ
    -0.08
    æĿ¥å¾ĹåıĬ
    -0.08
    ruz
    -0.08
    ³
    -0.08
    POSITIVE LOGITS
    à¸Ńาศัย
    0.11
    lessly
    0.10
     vả
    0.10
    ä¾Ŀèµĸ
    0.10
    å¾Ĺä½ı
    0.09
    æŶéĹ´æĿ¥
    0.09
     rely
    0.09
    ä¾ĿéĿł
    0.09
    äºİæѤ
    0.08
     relies
    0.08
    Activations Density 0.038%

    No Known Activations