© 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. 34596
    Prev
    Next
    INDEX
    Explanations

    past years

    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
    ä¸Ĭä¸ĭ
    -0.09
    çģ¶
    -0.09
    鸢
    -0.09
    ä¸ĭ车
    -0.09
    çIJ¼
    -0.08
    åĨį说
    -0.08
    éĽĢ
    -0.08
    åīįåIJİ
    -0.08
    isex
    -0.08
    ä»ij
    -0.08
    POSITIVE LOGITS
    夸
    0.10
    ÏĮ
    0.09
    æľīä¸Ģå®ļ
    0.09
    æľīå¾Ī大çļĦ
    0.09
    æľīä¸įåIJĮçļĦ
    0.09
    amus
    0.08
    æĺ¯ä¸Ģ座
    0.08
    å±ĢéĿ¢
    0.08
    ä»»ä½ķæŶåĢĻ
    0.08
    èĥĮä¸Ĭ
    0.08
    Activations Density 0.117%

    No Known Activations