© 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. 29675
    Prev
    Next
    INDEX
    Explanations

    in for a

    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
    etheless
    -0.09
    åĪ°æľĢåIJİ
    -0.09
    éħįæľī
    -0.09
    venience
    -0.08
    otte
    -0.08
    éĺĶ
    -0.08
    tim
    -0.08
    emies
    -0.08
    èĦĸ
    -0.08
    udent
    -0.08
    POSITIVE LOGITS
    /ext
    0.11
    çľĭçĤ¹
    0.10
    æĮijæĪĺ
    0.09
    egment
    0.09
    avit
    0.09
    èĢĥéªĮ
    0.09
    .serializer
    0.09
     Zug
    0.08
     ê·¸ëłĩ
    0.08
    urn
    0.08
    Activations Density 0.003%

    No Known Activations