© 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. 609
    Prev
    Next
    INDEX
    Explanations

    leaves or descriptors

    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
    çİ»
    -0.09
    æĪ¡
    -0.09
    çİīç±³
    -0.08
    orr
    -0.08
    æĺ¯éĿŀ
    -0.08
     Dover
    -0.08
    çķªèĮĦ
    -0.08
     centr
    -0.08
    èľ»
    -0.08
    ии
    -0.08
    POSITIVE LOGITS
    æłijåı¶
    0.14
    åľľ
    0.10
    åIJĮåŁİ
    0.10
    æĿª
    0.10
    诤
    0.10
    åı¶åŃIJ
    0.10
    水墨
    0.09
     bark
    0.09
    æ´Ĺ
    0.09
    à¸ģระà¹ģส
    0.09
    Activations Density 0.079%

    No Known Activations