© 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. 35903
    Prev
    Next
    INDEX
    Explanations

    be or is followed by adjective

    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
    ç½²
    -0.11
    好ä¸į好
    -0.09
    çĶľçĶľ
    -0.09
    urable
    -0.09
    åı©
    -0.09
    èĥĮçĿĢ
    -0.09
    å¦ĤæľŁ
    -0.09
    è¦ģçľĭ
    -0.09
    æ¿Ĵ临
    -0.09
    éĺ´å½±
    -0.09
    POSITIVE LOGITS
    inq
    0.09
     reason
    0.08
     Bard
    0.08
    NM
    0.08
     Allison
    0.08
    uje
    0.08
     Politico
    0.08
    иваеÑĤ
    0.08
    ç·£
    0.07
     ÑĦон
    0.07
    Activations Density 0.350%

    No Known Activations