© 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. 759
    Prev
    Next
    INDEX
    Explanations

    obj breeds

    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
    astica
    -0.08
    ica
    -0.07
    utre
    -0.07
    _plural
    -0.07
    çļĦ次æķ°
    -0.07
    è·ŁåĽ¢
    -0.06
    å·¥ä½ľæ»¡
    -0.06
    izzo
    -0.06
    apult
    -0.06
    é¦Ī
    -0.06
    POSITIVE LOGITS
    æĮ¨
    0.09
    oman
    0.07
    æĪij家çļĦ
    0.07
    ieger
    0.07
    ihal
    0.07
    ackt
    0.07
    eel
    0.07
    æĥĭ
    0.07
    .spatial
    0.07
    ë²Ī
    0.07
    Activations Density 0.203%

    No Known Activations