© 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. 6989
    Prev
    Next
    INDEX
    Explanations

    propidium iodide

    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
    orst
    -0.08
    anine
    -0.07
     lá
    -0.07
    åĴ«å°º
    -0.07
    pid
    -0.07
    uens
    -0.07
    assem
    -0.07
    /place
    -0.07
    UAN
    -0.07
    usty
    -0.06
    POSITIVE LOGITS
     Orth
    0.08
    Orth
    0.08
    约æĿŁ
    0.08
     constraint
    0.07
    constraint
    0.07
    bidden
    0.07
    exus
    0.07
    åѦåłĤ
    0.07
    constraints
    0.07
    Constraint
    0.07
    Activations Density 0.002%

    No Known Activations