© 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. 47471
    Prev
    Next
    INDEX
    Explanations

    concentration variations

    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
    è´§æºIJ
    -0.10
    åķĦ
    -0.09
     اÙĦØ®ÙĦ
    -0.09
    åIJĪä¼Ļ人
    -0.09
     vulgar
    -0.09
    åĥı个
    -0.09
    è¡į
    -0.08
    顶
    -0.08
    çĤ¹ç¼Ģ
    -0.08
    解æķ£
    -0.08
    POSITIVE LOGITS
    纤
    0.10
    erson
    0.10
    /cop
    0.09
    çĥ¤
    0.09
    opi
    0.09
    æĬĦ
    0.09
    驺
    0.09
    ç»ĩ
    0.09
    æĪĺçķ¥æĢ§
    0.08
    çªķ
    0.08
    Activations Density 0.129%

    No Known Activations