© 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. 29405
    Prev
    Next
    INDEX
    Explanations

    is a question or definition

    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
     Thousand
    -0.09
    åįıè°ĥ
    -0.09
    æ»ļæ»ļ
    -0.09
    误解
    -0.09
    ç¼ļ
    -0.08
    æĽ´æĺ¯
    -0.08
     intermediary
    -0.08
    ICC
    -0.08
    UBLE
    -0.08
    沸
    -0.08
    POSITIVE LOGITS
    æŀ¶
    0.09
    åħ¬å¼Ģåıijè¡Į
    0.09
    elman
    0.08
    临
    0.08
    æĭīå¼Ģ
    0.08
    åħĪ导
    0.08
    akah
    0.08
     unofficial
    0.08
    dings
    0.08
    caffold
    0.08
    Activations Density 0.039%

    No Known Activations