© 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. 37452
    Prev
    Next
    INDEX
    Explanations

    actual print size

    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
    åģ¿
    -0.08
    æľ¦
    -0.08
    AGEN
    -0.08
     xOffset
    -0.07
    å¤ĦçIJĨ设å¤ĩ
    -0.07
    è·ijæĿ¥
    -0.07
     dikat
    -0.07
    ihar
    -0.07
     bakal
    -0.07
    rica
    -0.07
    POSITIVE LOGITS
     chứ
    0.12
    èĢĮä¸įæĺ¯
    0.11
     rather
    0.10
    èĢĮéĿŀ
    0.10
     ÙĪÙĦÙĬس
    0.10
     ÙĪÙĦÙĬ
    0.09
     *
    0.09
     discrete
    0.08
     entire
    0.08
    rather
    0.08
    Activations Density 0.018%

    No Known Activations