© 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. 26037
    Prev
    Next
    INDEX
    Explanations

    when or wenn

    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
    ãģĹãģ¾ãģĨ
    -0.12
    ampa
    -0.10
    ãģĹãģ¾
    -0.09
    龸
    -0.09
    çİĽ
    -0.09
    æĤ¯
    -0.09
    åĥ»
    -0.09
    åĢļ
    -0.09
    avel
    -0.08
    ä»ĺãģij
    -0.08
    POSITIVE LOGITS
    çĶŁåij½
    0.09
     Walton
    0.09
    å±Ģéĥ¨
    0.09
    .ide
    0.08
     unst
    0.08
    å¾µ
    0.08
    ä¸Ģ头
    0.08
    éĽĨåĽ¢æĹĹä¸ĭ
    0.08
    æħ
    0.08
    æİĴ骨
    0.07
    Activations Density 0.001%

    No Known Activations