© 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. 1741
    Prev
    Next
    INDEX
    Explanations

    every followed by common words

    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
    æľĶ
    -0.10
    å¾Īé«ĺ
    -0.09
    ä¸įä¸Ģæł·çļĦ
    -0.09
    çĶŁäº§åĴĮ
    -0.09
    è½»æĺĵ
    -0.09
    人äºĭ
    -0.09
    arity
    -0.09
    主è¦ģåĮħæĭ¬
    -0.09
    æĥħ趣
    -0.08
    .booking
    -0.08
    POSITIVE LOGITS
    ä¸įèµ·
    0.10
    æ¯ıä¸Ģ个
    0.10
    tron
    0.09
     every
    0.09
    opper
    0.08
    LING
    0.08
    alette
    0.08
    lor
    0.08
    mund
    0.08
    举åĬ¨
    0.08
    Activations Density 0.002%

    No Known Activations