© 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. 6066
    Prev
    Next
    INDEX
    Explanations

    week followed by number or punctuation

    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
    ç»ĵå±Ģ
    -0.10
    屿
    -0.09
    åĢij
    -0.09
    é¹°
    -0.09
    妥åĸĦ
    -0.09
    åĨĪ
    -0.09
     EAR
    -0.08
    _peak
    -0.08
    çķĻä¸ĭæĿ¥
    -0.08
    峡
    -0.08
    POSITIVE LOGITS
    俾
    0.09
    jid
    0.08
     lone
    0.08
    è¿ĩåIJİ
    0.08
    æĬĺ
    0.08
    Wiki
    0.08
    tid
    0.08
    .snap
    0.08
    дÑĥм
    0.08
    avy
    0.08
    Activations Density 0.012%

    No Known Activations