© 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. 37683
    Prev
    Next
    INDEX
    Explanations

    promote

    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
    istics
    -0.07
    antry
    -0.07
    ointments
    -0.07
    à¹Ģà¸Ľà¸¥à¹Īา
    -0.07
    zaam
    -0.07
    arness
    -0.07
    大åı¯
    -0.07
    ides
    -0.07
    ities
    -0.07
    -0.07
    POSITIVE LOGITS
    etheus
    0.11
    ÑĥÑīеÑģÑĤв
    0.08
    enade
    0.08
    ulus
    0.08
    pong
    0.08
    oins
    0.08
    à¸īะà¸Ļัà¹īà¸Ļ
    0.08
    éĬ·
    0.08
    ehl
    0.08
    inent
    0.07
    Activations Density 0.031%

    No Known Activations