© 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. 58773
    Prev
    Next
    INDEX
    Explanations

    integers in arrays

    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
    ry
    -0.07
    isable
    -0.07
    so
    -0.07
    wright
    -0.06
    ilit
    -0.06
    zil
    -0.06
    æĪijåIJij
    -0.06
    i
    -0.06
    åľ°åIJij
    -0.06
    åį³åĪ°
    -0.06
    POSITIVE LOGITS
    edan
    0.08
    ság
    0.08
    ÐĿС
    0.08
    een
    0.08
    vik
    0.08
    einander
    0.08
    ona
    0.07
    ibera
    0.07
    TestData
    0.07
    ĥģ
    0.07
    Activations Density 0.008%

    No Known Activations