© 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. 59211
    Prev
    Next
    INDEX
    Explanations

    enjoy

    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
    оÑĩно
    -0.09
    NES
    -0.09
    å¾Īåĸľæ¬¢
    -0.09
    ç½ijåıĭè¯Ħ论
    -0.09
    æĹłè¾ľ
    -0.09
    çļĦä¿¡å¿ĥ
    -0.09
    好æľĭåıĭ
    -0.09
    éĻ¢æł¡
    -0.09
    æĥ³è¿ĩ
    -0.08
    åIJĥè¿ĩ
    -0.08
    POSITIVE LOGITS
    ably
    0.09
    éĺĹ
    0.08
    isis
    0.08
     liá»ģn
    0.08
    éĺ¶
    0.08
     Serv
    0.08
     Trou
    0.08
    çĶ¡
    0.07
    _RESP
    0.07
    ढ
    0.07
    Activations Density 0.007%

    No Known Activations