© 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. 37776
    Prev
    Next
    INDEX
    Explanations

    line 29

    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
    Not in Any Lists

    No Comments

    Negative Logits
    -0.06
    eed
    -0.06
    é£İ
    -0.06
    L
    -0.06
    EL
    -0.06
     L
    -0.06
     (
    -0.06
    CF
    -0.05
     intr
    -0.05
     Zimmerman
    -0.05
    POSITIVE LOGITS
    ë¬ĺ
    0.09
    cire
    0.09
    ç¾Ķ
    0.08
    еме
    0.08
    ouro
    0.08
     Fuse
    0.08
    gency
    0.08
    etus
    0.08
    ingleton
    0.08
    över
    0.08
    Activations Density 0.005%

    No Known Activations