© 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. 53930
    Prev
    Next
    INDEX
    Explanations

    time elapsed now

    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
    侯
    -0.11
    çļĦåIJĮæŶ
    -0.10
    è³´
    -0.10
    åĢĻ
    -0.10
    篱
    -0.09
    çļĦåīįæıIJä¸ĭ
    -0.09
    PIO
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    ä¸Ģæĸ¹
    -0.08
    lr
    -0.08
    POSITIVE LOGITS
    æľī个
    0.09
    tant
    0.09
    ymb
    0.08
     Gilles
    0.08
    ç¬ĶèĢħ
    0.08
     Cle
    0.08
    ilon
    0.08
    对äºİæĪij们
    0.08
    ils
    0.08
    yal
    0.08
    Activations Density 0.010%

    No Known Activations