© 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. 40211
    Prev
    Next
    INDEX
    Explanations

    alcoholic content

    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
     Stam
    -0.10
    ç±³ç²ī
    -0.09
    VIP
    -0.09
    éĺĢ
    -0.09
    wu
    -0.08
    aron
    -0.08
    海滩
    -0.08
    èĿİ
    -0.08
     adopt
    -0.08
    èıŁ
    -0.08
    POSITIVE LOGITS
    æµĵ缩
    0.10
    æĪIJåĵģ
    0.09
    Ñĥк
    0.09
    ((_
    0.09
    AZE
    0.09
    转弯
    0.09
    çŃī级
    0.09
     BaseType
    0.09
     taxing
    0.08
    è£½ä½ľ
    0.08
    Activations Density 0.077%

    No Known Activations