© 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. 44502
    Prev
    Next
    INDEX
    Explanations

    Osage Trail, mamayev Kurgan, Tumanovo

    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
    çĶĺéľ²
    -0.07
    ukt
    -0.07
    VML
    -0.07
    eneg
    -0.06
    aid
    -0.06
    ież
    -0.06
    没æĶ¶
    -0.06
    rov
    -0.06
    apos
    -0.06
     cannon
    -0.06
    POSITIVE LOGITS
    è¿Ļ个åIJįåŃĹ
    0.08
    ppet
    0.08
    idency
    0.08
    forc
    0.08
    WithName
    0.07
    åĢĻ
    0.07
     atrac
    0.07
    å¥ĩæĢª
    0.07
    æį¢ä¸ª
    0.07
    ìŀĩ
    0.07
    Activations Density 0.070%

    No Known Activations