© 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. 607
    Prev
    Next
    INDEX
    Explanations

    transitioning from... to

    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
    å¢
    -0.07
    ogue
    -0.07
     Rivers
    -0.06
    åIJĮ级
    -0.06
    hs
    -0.06
    å³
    -0.06
    ÑĤÑĭ
    -0.06
     ahead
    -0.06
    ux
    -0.06
    oon
    -0.06
    POSITIVE LOGITS
    —from
    0.26
    ä»İä¸Ģ个
    0.19
    ä»İæĹł
    0.17
    åľ°ä»İ
    0.16
    ä»İéĩį
    0.16
    -from
    0.15
    ä»İ
    0.15
    ä»İ天
    0.15
     transitioning
    0.14
    ä»İé«ĺ
    0.14
    Activations Density 0.305%

    No Known Activations