© 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. 40398
    Prev
    Next
    INDEX
    Explanations

    interviews conducted with 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
    èĥ¤
    -0.10
    иÑĪ
    -0.09
    ews
    -0.09
    ยว
    -0.09
    figures
    -0.09
     hứng
    -0.09
    adera
    -0.09
     vá»±c
    -0.09
    _mex
    -0.08
    è§Ī
    -0.08
    POSITIVE LOGITS
    访è°Ī
    0.12
    å½ķéŁ³
    0.10
    ä¸ĢåIJ¬
    0.10
    æĸ¹è¨Ģ
    0.10
    离éĢĢä¼ij
    0.10
    èĢģé¾ĦåĮĸ
    0.09
    èĢģ人
    0.09
    åIJ¬å¾Ĺ
    0.09
    éĿ¢è¯ķ
    0.09
     interview
    0.09
    Activations Density 0.039%

    No Known Activations