© 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. 52204
    Prev
    Next
    INDEX
    Explanations

    the best / first / only / same / safest

    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
    èĪįå¾Ĺ
    -0.08
     almost
    -0.08
    Ken
    -0.08
    大æ¦Ĥæĺ¯
    -0.08
    ä¸į管æĺ¯
    -0.08
    rok
    -0.08
    æĹłè®ºæĺ¯
    -0.08
    å·®ä¸įå¤ļ
    -0.08
    Frameworks
    -0.08
    åĿļæĮģ
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.13
    ä¸ĢåĽŀäºĭ
    0.12
    æ»ĭåij³
    0.11
    epad
    0.11
    ãģ©ãģĵãĤį
    0.10
    æ°´æµģ
    0.10
    åħ¸
    0.10
    eworthy
    0.10
    ä¹Łä¸įæĺ¯
    0.10
    withstanding
    0.09
    Activations Density 0.027%

    No Known Activations