© 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. 539
    Prev
    Next
    INDEX
    Explanations

    be used

    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
    ed
    -0.09
    为éģ¿åħį
    -0.08
    dae
    -0.08
     замÑĭ
    -0.08
    istan
    -0.07
    istribu
    -0.07
    imate
    -0.07
    mente
    -0.07
    大åĪ°
    -0.07
    itte
    -0.07
    POSITIVE LOGITS
    avior
    0.09
    /from
    0.09
    覧
    0.08
    ebut
    0.08
    ijing
    0.07
    SError
    0.07
    -même
    0.07
    aviour
    0.07
    å°Ķæĸ¯
    0.07
    åĿĢ
    0.07
    Activations Density 0.139%

    No Known Activations