© 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. 692
    Prev
    Next
    INDEX
    Explanations

    with the addition of

    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
    é¢ĩ
    -0.08
    zcze
    -0.08
    éĢĿ
    -0.08
    ä¹İ
    -0.08
    åIJĦèĩª
    -0.08
     wis
    -0.08
    裸
    -0.07
    --------------------------------------------------------------------------↵
    -0.07
    wis
    -0.07
    æīĢè°ĵ
    -0.07
    POSITIVE LOGITS
    贯穿
    0.11
    åģ·
    0.10
    xmlns
    0.09
    çĪ±å°Ķ
    0.09
    åĬłä¸Ĭ
    0.09
    åĽłèĢĮ
    0.09
    à¸Īำ
    0.09
    icc
    0.09
    åħħåĪĨåıijæĮ¥
    0.08
    æī¿è®¤
    0.08
    Activations Density 0.092%

    No Known Activations