© 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. 40082
    Prev
    Next
    INDEX
    Explanations

    edition

    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
    åħ¬çĦ¶
    -0.10
    æĪ¢
    -0.10
     Lantern
    -0.09
    ç»ıèIJ¥ç®¡çIJĨ
    -0.09
    lard
    -0.09
    å¿ĥ头
    -0.09
    rette
    -0.09
     trib
    -0.09
    åIJ¬è¯´
    -0.09
    åIJij社ä¼ļ
    -0.09
    POSITIVE LOGITS
    稿
    0.10
    åįŁ
    0.09
    æī¬
    0.08
    papers
    0.08
    åĬ¡
    0.08
    å¤ľéĹ´
    0.08
    éĶ¦
    0.08
    çķ´
    0.08
    aisy
    0.08
    uant
    0.08
    Activations Density 0.003%

    No Known Activations