© 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. 50734
    Prev
    Next
    INDEX
    Explanations

    non-english characters or symbols

    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
     thôi
    -0.08
    ORK
    -0.08
     rued
    -0.08
     شب
    -0.07
    åĴĮç½ij绾
    -0.07
    ortun
    -0.07
    üte
    -0.07
    assel
    -0.07
    è°ģçŁ¥éģĵ
    -0.07
     Silv
    -0.07
    POSITIVE LOGITS
    å¿ĥåľ°
    0.08
    ä¿ı
    0.07
    коми
    0.07
    ä¸Ģ票
    0.06
    μοÏħ
    0.06
    redirect
    0.06
    ¶
    0.06
     |–
    0.06
    å·®åĪĨ
    0.06
    áĥĺáĥĽ
    0.06
    Activations Density 0.003%

    No Known Activations