© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59818
    Prev
    Next
    INDEX
    Explanations

    clock signals

    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
    Negative Logits
     Lyn
    -0.06
    åı¯ä¹IJ
    -0.06
     comp
    -0.06
     assigned
    -0.06
    å¿į
    -0.06
     competitive
    -0.06
    鸥
    -0.06
    ç®ķ
    -0.06
    åı¸
    -0.06
    ifiable
    -0.06
    POSITIVE LOGITS
    æľ¬èº«
    0.10
    æľ¬èº«çļĦ
    0.10
    haus
    0.09
     itself
    0.09
     partenza
    0.08
    imson
    0.08
    ä½łèº«è¾¹
    0.08
    æľ¬äºº
    0.08
     shar
    0.08
    UnderTest
    0.08
    Activations Density 0.051%

    No Known Activations