© 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. 29515
    Prev
    Next
    INDEX
    Explanations

    exactly how or what

    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
    表éĿ¢ä¸Ĭ
    -0.09
    åħ¸åŀĭ
    -0.09
    峡
    -0.08
    åħ¸åŀĭçļĦ
    -0.08
     WG
    -0.08
    å¹²äºĭ
    -0.08
    佯
    -0.08
    бÑĢо
    -0.08
    çĺŁ
    -0.08
    åºı
    -0.08
    POSITIVE LOGITS
    exo
    0.10
    ä¸ĢåĽŀäºĭ
    0.10
    ÑĩиÑģлен
    0.09
    ensual
    0.09
    ç¿ķ
    0.09
    åĽ½æĥħ
    0.09
    æĭ©
    0.09
    èĥ½åĬĽåĴĮ
    0.09
    æĸ¹å¼ıè¿Ľè¡Į
    0.09
    åįģåĩłä¸ª
    0.08
    Activations Density 0.006%

    No Known Activations