© 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. 54347
    Prev
    Next
    INDEX
    Explanations

    then + subject

    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¸įæħİ
    -0.10
    then
    -0.09
    çĦ¶åIJİ
    -0.09
    اغ
    -0.09
    élé
    -0.08
    otts
    -0.08
    ãģĿãģĹãģ¦
    -0.08
    é£ı
    -0.08
     then
    -0.08
    äºį
    -0.08
    POSITIVE LOGITS
    æ¯ĭ
    0.10
    æµģåIJij
    0.09
    ized
    0.09
    cert
    0.09
    顯
    0.09
    ÑĢеÑģÑĤ
    0.09
     hiá»ĥn
    0.09
    羣çĪ±
    0.08
    æĸ½å·¥åįķä½į
    0.08
    æĹłçĸij
    0.08
    Activations Density 0.028%

    No Known Activations