© 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. 11661
    Prev
    Next
    INDEX
    Explanations

    competed in olympics

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.09
    æľ¬ç«Ļ
    -0.08
    ä¸Ģçīĩ
    -0.08
    çĤĴ
    -0.08
    ENER
    -0.08
    ×Ļ×Ļת
    -0.08
    梢
    -0.08
    åĺ»åĺ»
    -0.08
    太快
    -0.08
    åĬŁ
    -0.08
    POSITIVE LOGITS
    æ¿ĢçĥĪçļĦ
    0.10
    _processes
    0.10
    çī¹æľĹ
    0.10
    ining
    0.10
    åİ»è¿ĩ
    0.09
    æ¿ĢçĥĪ
    0.09
    åľ¨åĨħçļĦ
    0.09
    æĹ©æĹ¥
    0.09
    競
    0.09
    èī³
    0.09
    Activations Density 0.042%

    No Known Activations