© 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. 40779
    Prev
    Next
    INDEX
    Explanations

    stop words and punctuation

    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
    æĹ¥åħ¬å¸ĥ
    -0.09
    ontro
    -0.08
    åĬłåħ³æ³¨
    -0.08
     ë§ŀ춰
    -0.07
    åı«ä»ĸ
    -0.07
    óg
    -0.07
    ÑĤÑİ
    -0.07
    .Convert
    -0.07
    è¡·
    -0.07
    å¦ĤæĦı
    -0.07
    POSITIVE LOGITS
    ä¸įåĨį
    0.12
    åģľæŃ¢
    0.11
    åĨįä¹Ł
    0.10
    stop
    0.10
    ä¸įè¦ģåĨį
    0.10
    ä¸įåĨįæľī
    0.09
     stop
    0.09
     STOP
    0.09
    æľĢåIJİä¸Ģ次
    0.09
     Stop
    0.08
    Activations Density 0.026%

    No Known Activations