© 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. 63790
    Prev
    Next
    INDEX
    Explanations

    bloody

    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
    æѤåĪ»
    -0.11
    ÙĥÙĦ
    -0.10
    ãģ¤ãģĦ
    -0.09
    mob
    -0.09
    IONS
    -0.09
    ë¹Ļ
    -0.09
    Ùģت
    -0.09
    æŀķ头
    -0.08
    flix
    -0.08
    ели
    -0.08
    POSITIVE LOGITS
     minded
    0.10
    orgen
    0.10
    -minded
    0.10
    伤åı£
    0.10
    ç¬ijè¯Ŀ
    0.09
     ë¶Ī구íķĺê³ł
    0.09
    伤å¿ĥ
    0.09
    inburgh
    0.09
    ened
    0.09
    åºŁè¯Ŀ
    0.09
    Activations Density 0.008%

    No Known Activations