© 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. 44573
    Prev
    Next
    INDEX
    Explanations

    case names and legal proceedings

    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
    s
    -0.07
    lig
    -0.07
    å¤ļ
    -0.07
     bur
    -0.06
    Lib
    -0.06
    bul
    -0.06
    ards
    -0.06
    avras
    -0.06
    sc
    -0.06
    lv
    -0.06
    POSITIVE LOGITS
    cox
    0.08
    ä¸Ĭ涨äºĨ
    0.08
    _GRA
    0.08
    æĸĩéĽĨ
    0.08
    毡
    0.07
    estin
    0.07
    ØŃر
    0.07
    çĽĸä¸ĸ
    0.07
    볬
    0.07
    umping
    0.07
    Activations Density 0.012%

    No Known Activations