© 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. 60784
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    çݲ
    -0.11
    å¾Īæĺ¯
    -0.09
    VERY
    -0.09
    èĩªçĦ¶èĢĮ
    -0.08
    横
    -0.08
    åĩ¹
    -0.07
    orra
    -0.07
     Wells
    -0.07
    åIJįåı«
    -0.07
    å¦Ĥæŀľè¯´
    -0.07
    POSITIVE LOGITS
    riad
    0.11
    icer
    0.10
    éļIJç§ģ
    0.10
    thing
    0.09
    ä¸Ģä¸ĭåŃIJ
    0.09
    æĺ¯åľ¨
    0.09
    管çIJĨä¸Ńå¿ĥ
    0.09
    ãģ®ãģĵãģ¨
    0.09
    éĴ³
    0.09
    ackson
    0.09
    Activations Density 0.007%

    No Known Activations