© 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. 12075
    Prev
    Next
    INDEX
    Explanations

    years and championships counts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æķ´å¤©
    -0.12
    äºĮ级
    -0.09
    è¿Ŀç«ł
    -0.09
    æľĪæľ«
    -0.09
    æľĪåºķ
    -0.09
    åħ¨åĽ½åIJĦåľ°
    -0.08
    æĸ°æĬĢæľ¯
    -0.08
    åĵįèµ·
    -0.08
    stor
    -0.08
    ened
    -0.08
    POSITIVE LOGITS
    两次
    0.16
    ä¸ī次
    0.14
    _years
    0.12
    ä¹Ŀå¹´
    0.11
    éĹ´éļĶ
    0.11
     years
    0.11
     twice
    0.10
     YEARS
    0.10
    å¤ļ次
    0.10
     Twice
    0.10
    Activations Density 0.106%

    No Known Activations