© 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. 52211
    Prev
    Next
    INDEX
    Explanations

    names after punctuation

    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
    nage
    -0.07
    ibraries
    -0.06
    gó
    -0.06
    ostar
    -0.06
    olate
    -0.06
    osting
    -0.06
    رج
    -0.06
    éľĢæıIJä¾Ľ
    -0.06
    ost
    -0.06
    ilot
    -0.06
    POSITIVE LOGITS
    森çļĦ
    0.08
    aign
    0.08
    è°±åĨĻ
    0.07
    æľĢæĸ°è¯Ħ论
    0.07
    èĹIJ
    0.07
    _starts
    0.07
     निरà¥į
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    _SETUP
    0.07
    森
    0.07
    Activations Density 0.054%

    No Known Activations