© 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. 24181
    Prev
    Next
    INDEX
    Explanations

    sports tournaments

    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
    dess
    -0.09
     Jens
    -0.08
    æĶ»
    -0.08
     jun
    -0.08
    代表大ä¼ļ
    -0.08
    æīĵåį¡
    -0.08
    çĮĸ
    -0.08
    Boom
    -0.08
    Ral
    -0.08
     amb
    -0.08
    POSITIVE LOGITS
    æļ¨
    0.11
    èIJ½ä¸ĭ
    0.09
    SupportedContent
    0.09
    å½ĴæĿ¥
    0.09
    idy
    0.08
    qué
    0.08
    -uri
    0.08
    éĽªå±±
    0.08
    ä¼ĺèī¯
    0.08
    箫
    0.08
    Activations Density 0.062%

    No Known Activations