© 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. 44461
    Prev
    Next
    INDEX
    Explanations

    .cls Unity statements

    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
    ivals
    -0.10
    èĮĥæĸĩç½ij
    -0.09
    สà¹Į
    -0.08
    ese
    -0.08
    俱ä¹IJéĥ¨
    -0.08
    rial
    -0.08
    estä
    -0.08
    çļĦ
    -0.08
    IMUM
    -0.08
    áĥ¡
    -0.08
    POSITIVE LOGITS
    enburg
    0.07
    weile
    0.07
     dozen
    0.07
     kelamin
    0.07
    utenant
    0.07
    wis
    0.07
    Ñĭми
    0.07
    asmine
    0.06
    incinn
    0.06
    wise
    0.06
    Activations Density 0.002%

    No Known Activations