© 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. 40045
    Prev
    Next
    INDEX
    Explanations

    would be

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Gatt
    -0.10
    åĪĨæĶ¯
    -0.09
    æĬķ票
    -0.09
     пÑĢодолж
    -0.09
    è¿Ķ
    -0.09
    ä¹Łåıªèĥ½
    -0.09
    竽
    -0.08
    annot
    -0.08
    éĢĨè¡Į
    -0.08
    åį±
    -0.08
    POSITIVE LOGITS
    èĮ¬
    0.10
    æĺ¯åľ¨
    0.10
    æĺ¯ä¸Ģ座
    0.09
    rael
    0.09
    æĺ¯ä¸ĢåIJį
    0.09
    egal
    0.09
    æĺ¯ä»Ģä¹Īåij¢
    0.09
    æĺ¯ä»Ģä¹Ī
    0.09
    åľ¨äºİ
    0.08
    æĺ¯ä¸Ģ
    0.08
    Activations Density 0.125%

    No Known Activations