© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34600
    Prev
    Next
    INDEX
    Explanations

    querydsl, jpa

    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
    fully
    -0.10
    ante
    -0.09
    mente
    -0.09
    annel
    -0.09
    kid
    -0.08
    精彩çļĦ
    -0.08
     Crown
    -0.08
    åħ¶æ¬¡æĺ¯
    -0.08
    æĺİæĺ¾çļĦ
    -0.08
    idas
    -0.08
    POSITIVE LOGITS
    å¿Ļç¢Į
    0.11
    à¸Ńà¸ĩ
    0.10
    们éĥ½
    0.10
    .motion
    0.10
    agh
    0.09
    iners
    0.09
    æİīäºĨ
    0.09
    ìį¨
    0.09
    ä¸ĢåĪĩéĥ½
    0.09
    iators
    0.09
    Activations Density 0.005%

    No Known Activations