© 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. 59250
    Prev
    Next
    INDEX
    Explanations

    legal verdicts and judgments

    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
     tipping
    -0.09
    羣æŃ£åģļåĪ°
    -0.09
    ä»Ģä¹Īåij¢
    -0.08
    iliary
    -0.08
    移åĪ°
    -0.08
    è
    -0.08
     Listings
    -0.08
    ied
    -0.08
    erness
    -0.08
    obic
    -0.08
    POSITIVE LOGITS
    累累
    0.11
    esi
    0.11
    PURE
    0.10
    naire
    0.10
    izin
    0.10
    女ç¥ŀ
    0.09
    naires
    0.09
    ä¸įå¿ĺ
    0.09
    owing
    0.09
    -seat
    0.09
    Activations Density 0.014%

    No Known Activations