© 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. 29667
    Prev
    Next
    INDEX
    Explanations

    silly, goofy, wacky

    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
    ives
    -0.09
    çĦ¶æĺ¯
    -0.09
    -visible
    -0.09
    ual
    -0.08
    gang
    -0.08
    æİĴ骨
    -0.08
    豺
    -0.08
    åĪį
    -0.08
    é£Ł
    -0.08
     mich
    -0.08
    POSITIVE LOGITS
    ibrary
    0.10
     hạng
    0.10
    quence
    0.10
    apsed
    0.10
    tics
    0.09
    NESS
    0.09
    ä¸ŃåĽ½åĪ¶éĢł
    0.09
    ness
    0.09
    chemy
    0.09
    à¹Ĩ
    0.09
    Activations Density 0.003%

    No Known Activations