© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47711
    Prev
    Next
    INDEX
    Explanations

    soar, soaring, majestic, hue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rig
    -0.09
    iating
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    aled
    -0.09
    æĸ¯åŁº
    -0.09
    paired
    -0.09
    -sized
    -0.09
    ä»Ģ麽
    -0.09
    оз
    -0.08
    iation
    -0.08
    POSITIVE LOGITS
    0.12
    fully
    0.11
    ugg
    0.11
    strup
    0.09
    imuth
    0.09
    NewLabel
    0.09
    liest
    0.09
    letic
    0.09
    loom
    0.09
    ãģ£ãģįãĤĬ
    0.09
    Activations Density 0.038%

    No Known Activations