© 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. 22546
    Prev
    Next
    INDEX
    Explanations

    first

    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
    å¡ŀå°Ķ
    -0.10
     ведÑĮ
    -0.09
    ény
    -0.09
    éĺĸ
    -0.09
    ç¾İ女
    -0.09
    ç¶ĵçĩŁ
    -0.09
    çIJħ
    -0.09
    å¿ĥ仪çļĦ
    -0.09
    ynos
    -0.09
    æµĵæµĵ
    -0.09
    POSITIVE LOGITS
    åIJĮç±»
    0.08
    ä¸ĸ
    0.08
    ameda
    0.08
     Ink
    0.07
    èĩªçĦ¶èĢĮ
    0.07
    çªģåĩº
    0.07
    WP
    0.07
    wor
    0.07
    OfType
    0.07
     ÑĦон
    0.07
    Activations Density 0.079%

    No Known Activations