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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37393
    Prev
    Next
    INDEX
    Explanations

    more

    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
     Higgins
    -0.08
    èĪį
    -0.08
    èĢģå©Ĩ
    -0.08
    榧
    -0.08
    èį·
    -0.08
    æįIJçĮ®
    -0.08
    é¬
    -0.07
     Dropbox
    -0.07
    绣
    -0.07
    è´Łè´£äºº
    -0.07
    POSITIVE LOGITS
    æĽ´åĥıæĺ¯
    0.14
    èĢĮæĺ¯
    0.13
     eher
    0.12
    æĽ´å¤ļçļĦæĺ¯
    0.12
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.10
    说æĺ¯
    0.10
    çľĩ
    0.10
     legalize
    0.09
    жи
    0.09
    æĽ´å¤§
    0.09
    Activations Density 0.183%

    No Known Activations