© 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. 19064
    Prev
    Next
    INDEX
    Explanations

    form of "is something"

    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
    URN
    -0.10
    çľĭçľĭ
    -0.10
    æ¯Ķéĩį
    -0.09
    豫
    -0.09
    å·¥ä½ľä½ľé£İ
    -0.09
    ÑĤеÑĢ
    -0.09
    umba
    -0.09
    éĢļæĬ¥
    -0.09
     arbitr
    -0.08
    èĥİ
    -0.08
    POSITIVE LOGITS
    å¤Ħåľ¨
    0.10
     supposed
    0.10
    æ¯ķç«Łæĺ¯
    0.10
    è¿Ļä¹Īä¹ħ
    0.09
    æİ¥åıĹäºĨ
    0.09
    æ²IJæµ´
    0.09
    åĩºèĩª
    0.09
    æ°ijèIJ¥ä¼ģä¸ļ
    0.09
    好ä¸į容æĺĵ
    0.09
     supposedly
    0.09
    Activations Density 0.106%

    No Known Activations