© 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. 60636
    Prev
    Next
    INDEX
    Explanations

    golf tournament

    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
    ordo
    -0.10
    çIJ´
    -0.09
    ÑģÑĤавлен
    -0.09
    仪
    -0.09
    Æ°ng
    -0.09
     каÑĤал
    -0.09
    rig
    -0.09
    è°IJ
    -0.08
    BAT
    -0.08
    Ùĥار
    -0.08
    POSITIVE LOGITS
     dripping
    0.09
    å·®å¼ĤåĮĸ
    0.09
    èĻIJ
    0.09
    ä¸įåĬ¨
    0.09
    éĤ®
    0.09
    çĪ±äºº
    0.09
    èī¯æĢ§
    0.09
    æĬķæĶ¾
    0.08
    personal
    0.08
    æİı
    0.08
    Activations Density 0.036%

    No Known Activations