© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47406
    Prev
    Next
    INDEX
    Explanations

    html table row `<tr>`

    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
    Negative Logits
    eenth
    -0.12
    uvre
    -0.11
    trust
    -0.10
    eds
    -0.10
     dÃłng
    -0.10
     ÑĤÑĢÑĥд
    -0.09
    -0.09
    	TokenName
    -0.09
    ding
    -0.09
    çķ¿
    -0.09
    POSITIVE LOGITS
    udeau
    0.11
    iggers
    0.10
    æĦıä¹īä¸Ĭ
    0.10
    /bus
    0.10
    ampoline
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.09
    ç¬Ļ
    0.09
    æ»ĵ
    0.09
    åī¯ä¹¦è®°
    0.09
    worthy
    0.09
    Activations Density 0.186%

    No Known Activations