© 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. 37474
    Prev
    Next
    INDEX
    Explanations

    patent numbers preceded by digits

    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
    èģĮä¸ļåѦéĻ¢
    -0.09
    atum
    -0.08
    客è§Ĥ
    -0.07
    aine
    -0.07
    .sex
    -0.07
    pane
    -0.07
    -valid
    -0.07
    å©Ģå¨ľ
    -0.07
     lump
    -0.07
    noten
    -0.07
    POSITIVE LOGITS
    tik
    0.06
    Digit
    0.06
    ধà§įযà§ĩ
    0.06
    /logger
    0.06
    umat
    0.06
     Digit
    0.06
    ories
    0.06
    åħ¬å¸ĥ
    0.06
    å¾Īå¿«çļĦ
    0.06
    éĽªå³°
    0.06
    Activations Density 0.002%

    No Known Activations