© 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. 29382
    Prev
    Next
    INDEX
    Explanations

    together we / with

    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
    æµģéĢļ
    -0.10
    Ñĩик
    -0.09
    ähr
    -0.09
    对æİ¥
    -0.09
    çªĦ
    -0.09
    æĩĤäºĭ
    -0.09
    عة
    -0.08
    cour
    -0.08
    è¾İ
    -0.08
    ableView
    -0.08
    POSITIVE LOGITS
    ç¥
    0.09
    æīĢèĥ½
    0.09
    弥补
    0.09
     Nicol
    0.09
    è´²
    0.09
    æĪĺèĥľ
    0.09
    çļĦåĬĽéĩı
    0.09
    ä¸Ģèµ·æĿ¥
    0.08
    ä¸Ģèµ·åİ»
    0.08
    åĬª
    0.08
    Activations Density 0.024%

    No Known Activations