© 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. 26059
    Prev
    Next
    INDEX
    Explanations

    bid protest

    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
    ized
    -0.10
    icing
    -0.09
    noinspection
    -0.09
    going
    -0.09
    atics
    -0.09
    ص
    -0.08
    éĩįå¿ĥ
    -0.08
    krit
    -0.08
    kop
    -0.08
    hel
    -0.08
    POSITIVE LOGITS
    irectional
    0.13
    رة
    0.10
    壶
    0.10
    å¾Ģäºĭ
    0.09
    bid
    0.09
    acy
    0.09
     Bid
    0.09
    åĪ¶åº¦æĶ¹éĿ©
    0.09
    ernet
    0.09
    umen
    0.09
    Activations Density 0.011%

    No Known Activations