© 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. 47451
    Prev
    Next
    INDEX
    Explanations

    ocean or city descriptions

    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
     Seymour
    -0.08
    ÑģÑĤо
    -0.08
    åŃIJå¼¹
    -0.08
    ä¹ł
    -0.08
    ç¿Ĵ
    -0.08
    ä¹Łä¸įæĥ³
    -0.08
    äºĮ楼
    -0.08
     casual
    -0.08
    ück
    -0.08
    ä¸į让
    -0.08
    POSITIVE LOGITS
    çľĭå¾Ĺ
    0.11
    åĪĨæķ£
    0.10
    ä¸Ģè§Ī
    0.10
    æ¦Ĥ
    0.10
    å®ļä½į
    0.09
     depress
    0.09
    coles
    0.09
    terra
    0.09
    èĬ
    0.09
    åķĨä¸ļ
    0.09
    Activations Density 0.052%

    No Known Activations