© 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. 59888
    Prev
    Next
    INDEX
    Explanations

    whether

    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
    rious
    -0.08
    aum
    -0.08
    éĶĢ
    -0.07
    inned
    -0.07
    è·Ŀ
    -0.07
    ä¸īæ¸ħ
    -0.07
     wik
    -0.07
    ald
    -0.06
     agu
    -0.06
    ÙĨاد
    -0.06
    POSITIVE LOGITS
    okal
    0.08
    okie
    0.08
    æĢ»ç«Ļ
    0.08
    صÙĬ
    0.08
    mera
    0.07
    ieux
    0.07
    orma
    0.07
    ãĥªãĥ¥ãĥ¼
    0.07
    otre
    0.07
    æľĪåħī
    0.07
    Activations Density 0.008%

    No Known Activations