© 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. 47588
    Prev
    Next
    INDEX
    Explanations

    publicly traded, listed, IPO

    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
    anst
    -0.09
    ç½
    -0.09
    ÑģÑĤанов
    -0.09
    ä¸Ĭ课
    -0.09
    åı¯èĥ½å¯¼èĩ´
    -0.09
    ä¸īæľŁ
    -0.08
    edge
    -0.08
    æĽĪ
    -0.08
    车祸
    -0.08
    çĶ¨é¤IJ
    -0.08
    POSITIVE LOGITS
    èī³
    0.09
    åij¨åĪĬ
    0.09
    æħ¨
    0.09
    ä»ĭ
    0.09
     Lambert
    0.09
    Catch
    0.08
    å¸ģ
    0.08
    ิà¸ĩ
    0.08
    ени
    0.08
     Ya
    0.08
    Activations Density 0.024%

    No Known Activations