© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52273
    Prev
    Next
    INDEX
    Explanations

    Vaux's Swift, Swallow Barn, gulliver

    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
    ilos
    -0.09
    sem
    -0.09
    LOT
    -0.09
    pons
    -0.09
    ä¸Ńæĸ¹
    -0.08
    åŁºçŁ³
    -0.08
     cords
    -0.08
    vice
    -0.08
    å°ıå¿ĥ
    -0.08
    åī¯æł¡éķ¿
    -0.08
    POSITIVE LOGITS
    é£ŀæī¬
    0.09
    æīij
    0.09
    æĬµ
    0.09
    åıĹ欢è¿İ
    0.09
    éª
    0.08
    鸥
    0.08
    å¾ģæ±ĤæĦıè§ģ
    0.08
     Ghost
    0.08
    åŀĥåľ¾
    0.08
    ÑĢенд
    0.08
    Activations Density 0.045%

    No Known Activations