© 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. 56857
    Prev
    Next
    INDEX
    Explanations

    drums, bass, drummer

    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
    èĪĮ
    -0.09
    /gtest
    -0.09
    èĬį
    -0.09
    รม
    -0.09
    éĻIJé¢Ŀ
    -0.09
    褰
    -0.09
    hek
    -0.09
    ZONE
    -0.09
    æĮ½
    -0.08
    èĪĮ头
    -0.08
    POSITIVE LOGITS
    fried
    0.09
     fro
    0.08
     Wire
    0.08
    çħ§äº®
    0.08
     laz
    0.08
    yes
    0.08
    西红
    0.08
    tal
    0.08
    è°±
    0.08
     boss
    0.08
    Activations Density 0.113%

    No Known Activations