© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22297
    Prev
    Next
    INDEX
    Explanations

    Deadpool, Wolverine, Miller, animated series

    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
    åı¤ä»Ĭ
    -0.09
    éľĸ
    -0.09
    spb
    -0.09
    ç¼ĵç¼ĵ
    -0.09
    æĪĸèĢħ说
    -0.09
     MAGIC
    -0.08
    é¢Ĺ
    -0.08
    æºľ
    -0.08
    æĦ¿
    -0.08
    indle
    -0.08
    POSITIVE LOGITS
    è´
    0.09
    æīĭå¥Ĺ
    0.09
    èµŃ
    0.09
    aison
    0.09
    æ´ģ
    0.08
    污
    0.08
     Zak
    0.08
    rone
    0.08
    éĢĢå½¹
    0.08
     Eis
    0.08
    Activations Density 0.097%

    No Known Activations