© 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. 30631
    Prev
    Next
    INDEX
    Explanations

    and more

    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
    erals
    -0.08
    æķ¦
    -0.08
     nas
    -0.08
     ins
    -0.08
     Gener
    -0.08
     Lal
    -0.08
     quadr
    -0.08
    ä¸įå¿į
    -0.08
     tatto
    -0.08
    bos
    -0.08
    POSITIVE LOGITS
     ×ķ×¢×ķ×ĵ
    0.10
    çĭ¬ä¸ĢæĹłäºĮ
    0.10
    è¿Ļåıªæĺ¯
    0.10
    许å¤ļ
    0.10
    亮çĤ¹
    0.09
    KHTML
    0.09
    æĽ´å¤ļ
    0.09
    åį¤
    0.09
    éĩįè¦ģåĽłç´ł
    0.09
    claimer
    0.09
    Activations Density 0.057%

    No Known Activations