© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52480
    Prev
    Next
    INDEX
    Explanations

    with the

    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
    åħļåĴĮåĽ½å®¶
    -0.09
    大家éĥ½åľ¨
    -0.09
     pageNo
    -0.09
    æĽ
    -0.08
    å°ijäºĨ
    -0.08
    wy
    -0.08
    æ¯ķç«Ł
    -0.08
    åİĨ
    -0.08
    èĢĮä¸Ķ
    -0.08
    ä¸į管æĺ¯
    -0.08
    POSITIVE LOGITS
    åĬŁå¤«
    0.10
    èººåľ¨åºĬä¸Ĭ
    0.10
     blanket
    0.09
    äºĭåIJİ
    0.09
    çĩ®
    0.09
    ั
    0.09
    羣æŃ£çļĦ
    0.08
    é£ĵ
    0.08
    仿
    0.08
    lated
    0.08
    Activations Density 0.050%

    No Known Activations