© 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. 33475
    Prev
    Next
    INDEX
    Explanations

    sentence start punctuation

    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
    è±ķ
    -0.08
    欸
    -0.08
    ä½ĵåĬĽ
    -0.08
    路人
    -0.08
    ë¿IJë§Į
    -0.08
    æĪ·å¤ĸ
    -0.07
    åĮ£
    -0.07
    urt
    -0.07
    éĢŀ
    -0.07
    åĮ
    -0.07
    POSITIVE LOGITS
    å½»
    0.09
    è¦ģ说
    0.09
    åģļä¸Ģ个
    0.09
    æģ³
    0.09
    åħļçļĦåįģä¹Ŀ
    0.09
    æĸ°å½¢åĬ¿
    0.08
    å°Ĭæķ¬
    0.08
    æĭ·
    0.08
    æĸ°å½¢åĬ¿ä¸ĭ
    0.08
    uada
    0.08
    Activations Density 0.505%

    No Known Activations