© 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. 35025
    Prev
    Next
    INDEX
    Explanations

    concentration, intensity, or units like /kg

    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
    Õ®
    -0.09
    IER
    -0.07
    为åŃ¦æł¡
    -0.07
    lesa
    -0.07
    odb
    -0.07
    æĪIJ交价
    -0.07
    "|
    -0.07
    relu
    -0.07
    bidden
    -0.07
    iebe
    -0.07
    POSITIVE LOGITS
    enner
    0.07
     notation
    0.07
     den
    0.07
    ANGO
    0.07
    adi
    0.06
    èĦļçļĦ
    0.06
    den
    0.06
    avig
    0.06
    atoon
    0.06
    ensen
    0.06
    Activations Density 0.001%

    No Known Activations