© 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. 7198
    Prev
    Next
    INDEX
    Explanations

    records for ray, line, atom

    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
    hei
    -0.08
    ility
    -0.08
    hini
    -0.08
    ilities
    -0.07
    lements
    -0.07
    ailles
    -0.07
    è°ģæĿ¥
    -0.07
    itev
    -0.07
    çĸ¡
    -0.07
    erals
    -0.07
    POSITIVE LOGITS
    åĭĩå¾Ģ缴åīį
    0.08
    æľ¬åĽŀçŃĶ
    0.08
    ¬ģ
    0.07
    åĭĭ
    0.07
    åľ¨åį³
    0.07
    otate
    0.07
    izzano
    0.06
    æķ£
    0.06
    ¬
    0.06
    image
    0.06
    Activations Density 0.148%

    No Known Activations