© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    awards and film credits

    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
    æ¸ħæī«
    -0.10
     Trades
    -0.09
    æĭįåįĸ
    -0.08
    rawid
    -0.08
    ahkan
    -0.08
    éĺŁåıĭ
    -0.08
    èĤĩ
    -0.08
    oud
    -0.08
    对èĩªå·±çļĦ
    -0.08
    iker
    -0.08
    POSITIVE LOGITS
    è§Ĥå½±
    0.19
    çľĭçĶµå½±
    0.19
    å½±éĻ¢
    0.18
    æĶ¾æĺł
    0.18
    票æĪ¿
    0.15
    çĶµå½±èĬĤ
    0.15
    çĶµå½±éĻ¢
    0.15
    çĶµå½±
    0.13
     film
    0.13
    ä¸Ĭæĺł
    0.13
    Activations Density 0.131%

    No Known Activations