© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50292
    Prev
    Next
    INDEX
    Explanations

    navigation links and posts

    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
    OOT
    -0.10
    çĶŁæ´»æĸ¹å¼ı
    -0.09
    HING
    -0.09
    unk
    -0.08
    ialect
    -0.08
    linky
    -0.08
    _signed
    -0.08
    лом
    -0.08
    -uri
    -0.08
    æŃ£å¸¸çļĦ
    -0.08
    POSITIVE LOGITS
    罨
    0.10
    PathComponent
    0.09
    .setView
    0.09
    å¤ĸåĽ½
    0.09
    æĬķæľº
    0.09
    说ä¸įåĩº
    0.09
    èIJ½åħ¥
    0.09
    æĻ¯å¾·
    0.08
    åģľä¸ĭ
    0.08
    äºĮç»´
    0.08
    Activations Density 0.015%

    No Known Activations