© 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. 47450
    Prev
    Next
    INDEX
    Explanations

    pulp magazines and suspension

    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
    ãĥ³ãĤ°
    -0.09
    ements
    -0.09
    akes
    -0.09
    è°´
    -0.08
    è´£
    -0.08
    忤
    -0.08
    igers
    -0.08
    æĸ
    -0.08
     InterruptedException
    -0.08
    ãĤĤãģĦãģĦ
    -0.08
    POSITIVE LOGITS
    è®¤çľŁåŃ¦ä¹ł
    0.10
    iness
    0.10
    otomy
    0.09
    isateur
    0.09
    ç³ľ
    0.09
    inary
    0.09
    ferred
    0.09
    itu
    0.09
    ä¸įåłª
    0.08
    éĺij
    0.08
    Activations Density 0.004%

    No Known Activations