© 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. 26316
    Prev
    Next
    INDEX
    Explanations

    action initiated or completed

    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
    ä»Ģä¹Īåij¢
    -0.10
    ãģ£ãģ¨
    -0.09
    ardon
    -0.08
     Hemp
    -0.08
    opsy
    -0.08
    andon
    -0.08
    olta
    -0.08
    åİ»è¿ĩ
    -0.08
    dash
    -0.08
    æ¯Ĥ
    -0.08
    POSITIVE LOGITS
    /generated
    0.10
    çĪ¸
    0.09
    åīįæīĢæľªæľī
    0.09
    0.09
    å½»
    0.09
    èĦijæµ·ä¸Ń
    0.08
    è¦ļãģĪ
    0.08
    ç®į
    0.08
    ervices
    0.08
    à¹Ģà¸Ńà¸ĩ
    0.08
    Activations Density 0.109%

    No Known Activations