© 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. 59259
    Prev
    Next
    INDEX
    Explanations

    inventor or waited

    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
    æµİåįĹ
    -0.09
    毫æĹłçĸij
    -0.09
     Rough
    -0.09
    åݨ
    -0.09
    erver
    -0.08
    lettes
    -0.08
    å»ļ
    -0.08
    ç¢Ĺ
    -0.08
    ERVER
    -0.08
     Dread
    -0.08
    POSITIVE LOGITS
     Lithuania
    0.11
    ÄĹ
    0.10
     Ly
    0.09
    æįĭ
    0.09
    lien
    0.09
     Lith
    0.09
    istring
    0.08
     Nr
    0.08
    uly
    0.08
     longest
    0.08
    Activations Density 0.068%

    No Known Activations