© 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. 6027
    Prev
    Next
    INDEX
    Explanations

    fast food, fashion, software

    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
    è¡·
    -0.11
    許
    -0.09
    zag
    -0.09
    ension
    -0.09
    éli
    -0.09
    uez
    -0.08
    æĤłæĤł
    -0.08
     unspecified
    -0.08
    EMON
    -0.08
    æļ´
    -0.08
    POSITIVE LOGITS
    iez
    0.09
    ãĤ«ãĥª
    0.09
     Cowboys
    0.08
     handc
    0.08
    ify
    0.08
    æĪIJåIJį
    0.08
    å¿ħä¸įåı¯
    0.08
    è¾ħ导åijĺ
    0.08
    igkeit
    0.08
    ifying
    0.08
    Activations Density 0.002%

    No Known Activations