© 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. 32350
    Prev
    Next
    INDEX
    Explanations

    and i / i

    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
    éĻĮ
    -0.09
    æľĢæĹ©çļĦ
    -0.08
    æľĢæĹ©
    -0.08
    æŁIJä¸Ģ
    -0.07
    4
    -0.07
    好似
    -0.07
    SourceType
    -0.07
    èįĥ
    -0.07
    portion
    -0.07
    å¤ļä¹Ī
    -0.07
    POSITIVE LOGITS
    éĤ£å°±æĺ¯
    0.30
    åĪĨåĪ«æĺ¯
    0.19
    å°±æĺ¯
    0.17
    å°±æĺ¯è¦ģ
    0.16
    å°±åľ¨äºİ
    0.15
    nam
    0.15
    æĺ¯ä»Ģä¹Īåij¢
    0.15
    便æĺ¯
    0.15
    å°±æĺ¯åľ¨
    0.14
     nämlich
    0.14
    Activations Density 0.061%

    No Known Activations