© 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. 7172
    Prev
    Next
    INDEX
    Explanations

    integral

    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
    hood
    -0.09
    sé
    -0.09
    s
    -0.09
    scape
    -0.09
    eah
    -0.08
    schild
    -0.08
    ç´łé¢ľ
    -0.08
    ataire
    -0.08
    edException
    -0.08
    suit
    -0.08
    POSITIVE LOGITS
    ation
    0.11
    sson
    0.10
    gnore
    0.08
    entos
    0.08
    ¹
    0.08
    umn
    0.08
    ernational
    0.08
    errupted
    0.08
    egral
    0.08
    itial
    0.08
    Activations Density 0.004%

    No Known Activations