© 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. 59425
    Prev
    Next
    INDEX
    Explanations

    method license information

    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
    åįĥä¸ĩåĪ«
    -0.08
    +-+-+-+-
    -0.08
    holm
    -0.08
    ãģĵãģĵãģ§
    -0.08
    æĬ½
    -0.08
    ä½ĥ
    -0.08
    itus
    -0.07
    endor
    -0.07
     recap
    -0.07
    ä¸Ģåij³
    -0.07
    POSITIVE LOGITS
    åĤ¬
    0.10
    erus
    0.10
     combo
    0.10
    å¨ij
    0.09
     Forums
    0.09
    бÑĭ
    0.09
     aras
    0.09
    缸åºĶçļĦ
    0.09
    ç¾ģ
    0.09
    èĭ¥å¹²
    0.08
    Activations Density 0.231%

    No Known Activations