© 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. 17445
    Prev
    Next
    INDEX
    Explanations

    past participle or "being"

    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
    çĥŃéĹ¹
    -0.09
    etsk
    -0.08
     Hind
    -0.08
     Ski
    -0.08
     Urs
    -0.08
    æįį
    -0.08
    æ´¥
    -0.08
    åħĪ导
    -0.08
    DO
    -0.08
    åı¸
    -0.08
    POSITIVE LOGITS
    è¦ģèĢĥèĻij
    0.12
    该项
    0.10
    æľīåºıæİ¨è¿Ľ
    0.09
    æīİå®ŀæİ¨è¿Ľ
    0.09
    ä¸¥æł¼çļĦ
    0.09
    èª¿æŁ¥
    0.09
    离å¼ĢäºĨ
    0.09
    oker
    0.09
    çİ°è¡Į
    0.09
    æĹ¥å¤ľ
    0.08
    Activations Density 0.051%

    No Known Activations