© 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. 6105
    Prev
    Next
    INDEX
    Explanations

    consistency, inconsistencies, football, quarterback, batch

    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
    ember
    -0.10
    çŃĸ
    -0.09
    è·Į
    -0.09
    bos
    -0.09
    _past
    -0.09
    éĤ¸
    -0.08
    enic
    -0.08
    èĵĦ
    -0.08
    .Stage
    -0.08
    éľĵ
    -0.08
    POSITIVE LOGITS
     consistent
    0.23
    ä¸Ģèĩ´æĢ§
    0.22
    ä¸Ģèĩ´
    0.22
     consistency
    0.21
    consistent
    0.20
    稳å®ļçļĦ
    0.20
    稳å®ļ
    0.20
    ç©©å®ļ
    0.19
     inconsistent
    0.18
    ä¸Ģè´¯
    0.17
    Activations Density 0.070%

    No Known Activations