© 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. 29626
    Prev
    Next
    INDEX
    Explanations

    conducting and performance

    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
    çŃ¹
    -0.09
    æĿ¥åĪ°
    -0.09
     spiked
    -0.09
    éľŃ
    -0.09
    VICE
    -0.08
    éħ°
    -0.08
    æºľ
    -0.08
     Châu
    -0.08
    å¡Į
    -0.08
    Ñģли
    -0.08
    POSITIVE LOGITS
    èĪŀ
    0.16
    èĪŀè¹Ī
    0.15
    æ¼Ķå¥ı
    0.13
     dance
    0.13
    å¥ı
    0.13
    dance
    0.13
     Dance
    0.13
    è·³èĪŀ
    0.12
     danced
    0.11
    à¹Ģà¸ŀลà¸ĩ
    0.11
    Activations Density 0.078%

    No Known Activations