© 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. 29625
    Prev
    Next
    INDEX
    Explanations

    positive descriptors + noun

    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
    粤
    -0.08
    ä¸ĢäºĮ
    -0.08
     deal
    -0.08
    deal
    -0.08
    è¶³å¤ŁçļĦ
    -0.08
    ÃŃd
    -0.08
     ÑĤÑĥ
    -0.08
    ée
    -0.08
    åĨ·ç¬ij
    -0.08
    angan
    -0.08
    POSITIVE LOGITS
    å°±è¿Ļä¹Ī
    0.10
    oster
    0.09
    çĪ¶åŃIJ
    0.09
    è¡Įä¸ļçļĦ
    0.09
    opers
    0.09
    Alternate
    0.09
     AUG
    0.08
    overrides
    0.08
    oice
    0.08
     Äiju
    0.08
    Activations Density 0.088%

    No Known Activations