© 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. 32277
    Prev
    Next
    INDEX
    Explanations

    technical terms and definitions

    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
    koop
    -0.08
    å¿Ĺ
    -0.08
     appunto
    -0.07
     neve
    -0.07
    ebles
    -0.06
    thag
    -0.06
    ãģ®ãģĵãģ¨
    -0.06
    à¸ģะ
    -0.06
    apter
    -0.06
    дие
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.13
    åIJĮæł·æĺ¯
    0.11
    ãģĵãģ¡ãĤīãĤĤ
    0.11
    åIJĮæł·
    0.10
    another
    0.10
    ãģĵãģ¡ãĤīãģ¯
    0.10
    åı¦ä¸Ģ个
    0.09
    åı¦ä¸Ģç§į
    0.09
    åı¦ä¸Ģ
    0.09
     another
    0.09
    Activations Density 0.199%

    No Known Activations