© 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. 55212
    Prev
    Next
    INDEX
    Explanations

    duration, width, thickness, time

    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
    verso
    -0.07
    è¡ĮåĪĹ
    -0.07
    ibles
    -0.07
    éħį
    -0.07
    å²Ń
    -0.07
    _distances
    -0.07
    mok
    -0.07
    кÑĢе
    -0.07
     Magistr
    -0.07
     mature
    -0.07
    POSITIVE LOGITS
    duration
    0.11
     duration
    0.11
    -width
    0.10
    宽度
    0.10
    寬
    0.10
    宽
    0.10
     width
    0.09
    宽çļĦ
    0.09
    åį³éĢĿ
    0.09
     overlap
    0.09
    Activations Density 0.077%

    No Known Activations