© 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. 47722
    Prev
    Next
    INDEX
    Explanations

    game topics and commands

    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
    ä¹Łå¥½
    -0.12
    磶
    -0.11
    åı¯çĪ±çļĦ
    -0.09
    plode
    -0.09
    æĿ¥ä¸įåıĬ
    -0.09
    ONA
    -0.09
    æ¡ł
    -0.09
    çĪĨçĤ¸
    -0.08
    æ¿ij
    -0.08
     заÑīиÑĤ
    -0.08
    POSITIVE LOGITS
    é¾Ļ头
    0.10
    Donate
    0.09
    å¥ł
    0.09
    èĥļ
    0.09
    èļģ
    0.08
    橱
    0.08
     epic
    0.08
    è¦ģ注æĦı
    0.08
    ç»´
    0.08
    åݨ
    0.08
    Activations Density 0.082%

    No Known Activations