© 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. 4592
    Prev
    Next
    INDEX
    Explanations

    s followed by equals sign

    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
    c
    -0.07
    atia
    -0.07
    hammer
    -0.07
    icients
    -0.07
    atique
    -0.07
    mag
    -0.07
    institut
    -0.07
    اÙĨ
    -0.07
    atine
    -0.07
    ëŀĮ
    -0.07
    POSITIVE LOGITS
    nyder
    0.09
    ifter
    0.09
    utherland
    0.09
    ushman
    0.09
    ive
    0.08
     Ñģобой
    0.08
    ottie
    0.07
    éĽĢè·ĥ
    0.07
    èĩ³æѤ
    0.07
    ynchronized
    0.07
    Activations Density 0.033%

    No Known Activations