© 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. 64096
    Prev
    Next
    INDEX
    Explanations

    Arizona, GOP, ASU

    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
    -fw
    -0.12
    åı¬éĽĨ
    -0.11
    æĭŁ
    -0.10
    habi
    -0.09
    骥
    -0.09
    æĦıä¹ī
    -0.09
    çĥŁåı°
    -0.08
    hrs
    -0.08
    оÑģÑĮ
    -0.08
    å¾Īå¿«
    -0.08
    POSITIVE LOGITS
    å±Ī
    0.09
    æij¸ç´¢
    0.09
    tem
    0.09
    Arizona
    0.09
    ä¸ĩéĩĮ
    0.08
    æĬµ
    0.08
    äºŃ
    0.08
     Arizona
    0.08
    èĢģ人家
    0.08
     Salisbury
    0.08
    Activations Density 0.132%

    No Known Activations