© 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. 7105
    Prev
    Next
    INDEX
    Explanations

    European language beginnings

    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
    inally
    -0.08
    slick
    -0.08
    наÑĩале
    -0.08
    моби
    -0.07
    ingkan
    -0.07
    ueux
    -0.07
    беÑĢкÑĥ
    -0.07
    -0.07
    ALLY
    -0.07
    лÑİми
    -0.07
    POSITIVE LOGITS
    ag
    0.08
    ej
    0.07
    ut
    0.07
    tin
    0.07
    it
    0.07
    eg
    0.07
    og
    0.07
    å¾Ĺ好
    0.07
    Ø·
    0.07
    iT
    0.07
    Activations Density 0.503%

    No Known Activations