© 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. 59939
    Prev
    Next
    INDEX
    Explanations

    units of measure and scientific notation

    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
    éĤ¸
    -0.07
    ä¸įä¸İ
    -0.07
    家家
    -0.07
    ä¸ĥçĻ¾
    -0.06
     shouldBe
    -0.06
    Surname
    -0.06
    å¿Ĺ强
    -0.06
    èĪ¬
    -0.06
    åłĨ
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    POSITIVE LOGITS
    _representation
    0.08
    aph
    0.08
    ä¾ĭå¦Ĥ
    0.07
    å½ĵå¹´
    0.07
     Paran
    0.07
    á»ıa
    0.07
    arella
    0.07
    .appspot
    0.07
    çķ¶å¹´
    0.07
     Bieber
    0.07
    Activations Density 0.015%

    No Known Activations