© 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. 20155
    Prev
    Next
    INDEX
    Explanations

    sentence ending 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¿Ļæĺ¯åĽłä¸º
    -0.11
    æ¥Ĥ
    -0.10
    -wow
    -0.10
    åħ¶ä»ĸçļĦ
    -0.10
    éĺ²ç©º
    -0.10
    åĺĽ
    -0.10
    ÑģÑĤ
    -0.10
    èįª
    -0.09
    wow
    -0.09
    éĥ½ä¸įèĥ½
    -0.09
    POSITIVE LOGITS
    aines
    0.08
    ä¸ĢæĹ¥
    0.08
     parted
    0.07
    æ°§
    0.07
    论
    0.07
    ä¸ĩåįļ
    0.07
     OTA
    0.07
    ðŁĪ
    0.07
    请
    0.07
    iti
    0.07
    Activations Density 0.092%

    No Known Activations