© 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. 19157
    Prev
    Next
    INDEX
    Explanations

    evaluating whether

    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
    æĮĩå®ļ
    -0.08
    꼬
    -0.07
    uchu
    -0.07
    chant
    -0.07
    ordes
    -0.07
     verlang
    -0.07
     Herv
    -0.07
    çļĦä»ĭç»į
    -0.07
    ampo
    -0.07
    à¤ĸà¥įया
    -0.07
    POSITIVE LOGITS
    è¯Ħä¼°
    0.12
    åĪ©å¼Ĭ
    0.12
    åĨ³å®ļæĺ¯åIJ¦
    0.12
     whether
    0.12
    èĢĥéĩı
    0.12
    æĺ¯åIJ¦ä¼ļ
    0.12
     evaluate
    0.11
    è¿Ľè¡Įè¯Ħä¼°
    0.11
     weighing
    0.11
    evaluate
    0.11
    Activations Density 0.181%

    No Known Activations