© 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. 4924
    Prev
    Next
    INDEX
    Explanations

    superlative completion 'ever'

    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
    å¾Īåĸľæ¬¢
    -0.10
    å¾Ī满æĦı
    -0.10
    åĥ®
    -0.09
    å®īåħ¨ä¿Ŀéļľ
    -0.09
     Äijủ
    -0.09
    aroo
    -0.09
    æĿ¥åİĨ
    -0.08
    è¶³å¤Ł
    -0.08
    æĸ¹æĸ¹éĿ¢
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    POSITIVE LOGITS
    -ever
    0.10
     ever
    0.10
    ever
    0.09
    è¿Ń
    0.09
    eter
    0.09
    åĬłä¸Ĭ
    0.09
    åIJĮè¡Į
    0.09
    åī¥
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
     TER
    0.08
    Activations Density 0.006%

    No Known Activations