© 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. 29738
    Prev
    Next
    INDEX
    Explanations

    screen, television, movie, show, fiction

    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
    å¸ĥ
    -0.09
    åħ¥ä¾µ
    -0.09
    ä¹łè¿ij
    -0.09
    æļĤ
    -0.09
    祷
    -0.08
    ä»İåīį
    -0.08
    allah
    -0.08
     açık
    -0.08
    èį£å¹¸
    -0.08
    ãĥĹ
    -0.08
    POSITIVE LOGITS
    è¿ĩäºİ
    0.10
    æĶ¹ç¼ĸ
    0.10
    ilog
    0.09
    èĬ¬
    0.09
    Verse
    0.09
    èĦ±
    0.08
    模çī¹
    0.08
    ç¼Ļ
    0.08
    å±ıå¹ķ
    0.08
    èĦ¾æ°Ķ
    0.08
    Activations Density 0.184%

    No Known Activations