© 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. 27439
    Prev
    Next
    INDEX
    Explanations

    cycling races Tour de France

    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
    chester
    -0.10
    heed
    -0.09
    æĴŀåĩ»
    -0.09
    æķŀ
    -0.09
    诸èijĽ
    -0.09
    æī¿æİ¥
    -0.09
    rawer
    -0.09
    åľ°ä¸ĭ
    -0.09
    æŁĶ
    -0.09
    æī©å¼ł
    -0.09
    POSITIVE LOGITS
    å°ıå¹ħ
    0.10
    errat
    0.09
    çĸ¾
    0.09
    æĢģ
    0.08
    è¯Ĩ
    0.08
    èĢģæĿ¿
    0.08
    å¿ĺ
    0.08
    å°ıçĻ½
    0.08
    æ´¾
    0.08
    å¢ĥåĨħ
    0.08
    Activations Density 0.094%

    No Known Activations