© 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. 59294
    Prev
    Next
    INDEX
    Explanations

    in terms of

    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
    èIJ½åľ°
    -0.10
    åī²
    -0.10
    港澳
    -0.09
    æľīæĦı
    -0.08
    港
    -0.08
     Rico
    -0.08
    çı¾åł´
    -0.08
    æľīåºı
    -0.08
    寻
    -0.08
    æĿ²
    -0.08
    POSITIVE LOGITS
     terms
    0.15
    terms
    0.11
    Terms
    0.10
    èģĮ称
    0.09
    /terms
    0.09
     Terms
    0.09
    æŀķ
    0.09
    ç±
    0.09
    éģĵçIJĨ
    0.09
    æľķ
    0.09
    Activations Density 0.196%

    No Known Activations