© 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. 47514
    Prev
    Next
    INDEX
    Explanations

    people

    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
    åŁİå¸Ĥ建设
    -0.10
    åħĪçĶŁ
    -0.10
    åı¯éĿłçļĦ
    -0.10
    çĿĢçľ¼äºİ
    -0.09
    å¾Īæ¼Ĥ亮
    -0.09
    OCK
    -0.09
    大家
    -0.09
    èĢģ人家
    -0.09
    è¿Ļ家ä¼Ļ
    -0.09
    åı¯éĿł
    -0.08
    POSITIVE LOGITS
    hip
    0.09
    IPH
    0.09
    æ³¢çī¹
    0.09
    å°¤åħ¶æĺ¯
    0.09
    çī¹åĪ«æĺ¯
    0.09
    rels
    0.08
    -turned
    0.08
    adem
    0.08
    .hasOwnProperty
    0.08
    å¹ķ
    0.08
    Activations Density 0.051%

    No Known Activations