© 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. 47540
    Prev
    Next
    INDEX
    Explanations

    predicting outcomes

    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
    åķ¾
    -0.10
    é²ľæĺİ
    -0.09
    umo
    -0.08
     Lanc
    -0.08
    à¸Ľà¸£à¸°
    -0.08
    对该
    -0.08
    ä¸ĵä¸ļæĬĢæľ¯
    -0.08
    åħ°
    -0.08
    ä¸ĢåľĪ
    -0.08
     coincidence
    -0.08
    POSITIVE LOGITS
    é¢Ħæµĭ
    0.13
     predict
    0.13
    æľªæĿ¥
    0.12
    .predict
    0.12
     predicts
    0.11
    é¢Ħè§ģ
    0.11
    predict
    0.11
     Predict
    0.11
    (predict
    0.11
     predicting
    0.11
    Activations Density 0.155%

    No Known Activations