© 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. 12190
    Prev
    Next
    INDEX
    Explanations

    strength of exercises

    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
    åĽŀäºĭ
    -0.10
    ation
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.09
    æĵIJ
    -0.09
    mie
    -0.09
    åįģå¤ļ
    -0.09
    åĦ¿
    -0.08
    åĩ»
    -0.08
    å¸ĮæľĽå¤§å®¶
    -0.08
    ision
    -0.08
    POSITIVE LOGITS
     mẽ
    0.13
    ened
    0.11
    haft
    0.10
    yles
    0.10
    holds
    0.10
    nad
    0.10
    fully
    0.09
    ful
    0.09
    éĽĦåİļ
    0.09
    æĦ§
    0.09
    Activations Density 0.025%

    No Known Activations