© 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. 1320
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
    oter
    -0.11
    é¢Ĩ
    -0.11
    çĶļä¹Ī
    -0.10
    æľīä»·åĢ¼çļĦ
    -0.09
    ä½İ头
    -0.09
    ottom
    -0.09
     strap
    -0.09
    纪å§Ķ书记
    -0.09
    æľīä»·åĢ¼
    -0.09
    éĩĮéĿ¢çļĦ
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.10
    æľīè¿Ļæł·çļĦ
    0.09
    åĽłåľ°åĪ¶å®ľ
    0.09
    burgh
    0.08
    è¿ĻäºĽéĥ½æĺ¯
    0.08
    _MAC
    0.08
    åĽłä¸ºåľ¨
    0.08
    çļĩå¸Ŀ
    0.08
     Haut
    0.08
    éĶļ
    0.07
    Activations Density 0.038%

    No Known Activations