© 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. 730
    Prev
    Next
    INDEX
    Explanations

    and followed by a word

    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
    åıĪæĺ¯
    -0.10
    nts
    -0.09
    nten
    -0.08
    ıkl
    -0.08
    _),
    -0.08
    ãģ°ãģĭãĤĬ
    -0.08
    æĭħ
    -0.08
    elin
    -0.08
    æĮ«æĬĺ
    -0.08
    .Authorization
    -0.08
    POSITIVE LOGITS
     how
    0.17
    å¦Ĥä½ķ
    0.15
     its
    0.14
    how
    0.13
     whether
    0.13
    èĥ½ä¸įèĥ½
    0.12
    æĺ¯å¦Ĥä½ķ
    0.12
    åıĬåħ¶
    0.12
    èĥ½åIJ¦
    0.12
    该å¦Ĥä½ķ
    0.12
    Activations Density 0.168%

    No Known Activations