© 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. 24350
    Prev
    Next
    INDEX
    Explanations

    by no means

    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
    å¿įåıĹ
    -0.09
    imary
    -0.09
    åĨįéĢł
    -0.08
     bid
    -0.08
    nees
    -0.08
    baugh
    -0.08
    snap
    -0.08
    gram
    -0.08
     Away
    -0.08
    RAL
    -0.08
    POSITIVE LOGITS
    è¿Ļæĺ¯ä¸Ģ个
    0.10
    ä¸įæĺ¯ä¸Ģ个
    0.10
    çĭ¬
    0.10
    å°±æĺ¯ä¸Ģ个
    0.09
    tps
    0.09
     Alive
    0.09
    æĺ¯ä¸Ģéĥ¨
    0.09
    å¿Ĵ
    0.09
    æĺ¯ä¸ĢåIJį
    0.09
    é«ĺå³°
    0.09
    Activations Density 0.010%

    No Known Activations