© 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. 56991
    Prev
    Next
    INDEX
    Explanations

    studies have

    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
    à¸Īาà¸ģà¸ģาร
    -0.10
    åħĦå¼Ł
    -0.09
    boot
    -0.09
    lew
    -0.09
     Coll
    -0.09
    CY
    -0.09
    lean
    -0.09
     lean
    -0.09
    åľ°å¸¦
    -0.09
    ç¥ĸåĽ½
    -0.08
    POSITIVE LOGITS
    roots
    0.10
    ä¸Ńæľī
    0.09
    ä¸ŃæľĢ
    0.09
     Roots
    0.09
    以æĿ¥
    0.09
    éľ²
    0.09
    ä¸ŃåŃĺåľ¨çļĦ
    0.08
    LK
    0.08
    饮水
    0.08
    ç²¾ç¥ŀ
    0.08
    Activations Density 0.276%

    No Known Activations