© 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. 39880
    Prev
    Next
    INDEX
    Explanations

    successful brands, easy to clean, Nikola Tesla

    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
    åIJĦ个æĸ¹éĿ¢
    -0.10
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    -0.09
    è´¨éĩıåĴĮ
    -0.09
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.09
    éĿŀ常好çļĦ
    -0.09
    éĤ£ç§į
    -0.09
    éĥ½èĥ½å¤Ł
    -0.08
    åģĥ
    -0.08
    ä¸ĢæŃ¥æŃ¥
    -0.08
    æĹłä¸į
    -0.08
    POSITIVE LOGITS
    eref
    0.09
    prü
    0.08
    ãģķãģĦ
    0.08
    ”:
    0.08
    .Solid
    0.08
    åĢĮ
    0.08
    near
    0.08
    çī¢
    0.08
    ÇĴ
    0.07
    â¦ģ
    0.07
    Activations Density 0.485%

    No Known Activations