© 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. 24249
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä¼ŀ
    -0.10
    æ·Ļ
    -0.09
    umb
    -0.09
    åĭ
    -0.08
    uiten
    -0.08
    ely
    -0.08
     mirrors
    -0.08
    cg
    -0.08
    èİĺ
    -0.08
    opp
    -0.08
    POSITIVE LOGITS
    å¼ĢèĬ±
    0.10
    ÄĻp
    0.09
    çµ®
    0.09
    ä¸ĢåĿĹ
    0.09
    /twitter
    0.09
    çĦ°
    0.09
    åī²
    0.09
     EVE
    0.08
    iks
    0.08
    èĽĭ
    0.08
    Activations Density 0.000%

    No Known Activations