© 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. 59410
    Prev
    Next
    INDEX
    Explanations

    parents groups and foundations

    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
    xon
    -0.08
    (floor
    -0.08
    deo
    -0.08
    stances
    -0.08
    .Factory
    -0.08
    odo
    -0.08
    ç»Īç»ĵ
    -0.08
    ãĥĨãĤ£ãĥ¼
    -0.08
    ly
    -0.08
    ToEnd
    -0.08
    POSITIVE LOGITS
    illos
    0.10
    è¾Ĺ转
    0.09
    è¿¢
    0.09
    åŃķ
    0.09
    驽
    0.09
    åIJģ
    0.09
    åIJ¬å¾Ĺ
    0.09
    å¹²äºĭ
    0.09
    æĹłå¿§
    0.09
    æĬķèµĦé¢Ŀ
    0.08
    Activations Density 0.002%

    No Known Activations