© 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. 63389
    Prev
    Next
    INDEX
    Explanations

    sports championships and team results

    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
    çĥĤ
    -0.10
    ä¸ļåĨħ人士
    -0.09
    ambi
    -0.09
    éĵĤ
    -0.09
    ainless
    -0.09
    trad
    -0.09
    bage
    -0.09
    éĢ
    -0.08
    popular
    -0.08
     energetic
    -0.08
    POSITIVE LOGITS
    å©¢
    0.09
    éĴĵ
    0.09
    å°ķ
    0.09
    éļIJå½¢
    0.09
     кÑĢай
    0.09
    çīµ
    0.08
    æ·Ģ
    0.08
    第ä¸Ģéĥ¨
    0.08
    æ¦ľé¦ĸ
    0.08
    лин
    0.08
    Activations Density 0.277%

    No Known Activations