© 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. 37685
    Prev
    Next
    INDEX
    Explanations

    phase transition

    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
    ervas
    -0.08
    è°
    -0.08
    rame
    -0.07
    pras
    -0.07
    =\"#
    -0.07
    åłª
    -0.07
    è¡Į使
    -0.07
    æĭĽäºº
    -0.07
    ç¬
    -0.07
    orian
    -0.07
    POSITIVE LOGITS
    æ±½
    0.08
    æ¯ıåħ¬æĸ¤
    0.08
    çĨĶåĮĸ
    0.07
     therm
    0.07
    é¢Ŀ
    0.07
    éĢĶ
    0.07
     thermal
    0.07
    transition
    0.07
    æĶ¯ä»ĺç»Ļ
    0.07
    æ±Ĺ
    0.07
    Activations Density 0.002%

    No Known Activations