© 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. 49831
    Prev
    Next
    INDEX
    Explanations

    Solicitor, advocate, judge roles

    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
    äºļ
    -0.09
    lep
    -0.09
    ycz
    -0.09
    unds
    -0.09
    è´¸æĺĵ
    -0.09
    äºŀ
    -0.09
    æĢģ
    -0.08
     Hispan
    -0.08
    çĤī
    -0.08
    kaar
    -0.08
    POSITIVE LOGITS
    åİĦ
    0.10
    çķĮ
    0.09
    çķĮçļĦ
    0.09
    å´Ń
    0.09
    ä¸ĵä¸ļåĮĸ
    0.09
    Coll
    0.08
    èĦĸåŃIJ
    0.08
    (docs
    0.08
    eron
    0.08
    é¢Ŀ
    0.08
    Activations Density 0.088%

    No Known Activations