© 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. 58401
    Prev
    Next
    INDEX
    Explanations

    place names ending in ville, ford, ton, or London

    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
    sic
    -0.09
    bei
    -0.09
    æ¡ĥèĬ±
    -0.09
    çĮ¢
    -0.08
    çĭ¸
    -0.08
    èĥĮéĥ¨
    -0.08
    ä¼ĹæīĢ
    -0.08
    åĨľå®¶ä¹IJ
    -0.08
    è¦ģçĤ¹
    -0.08
    aster
    -0.08
    POSITIVE LOGITS
    ãģ«ä¹Ĺ
    0.09
    æīĭèĩĤ
    0.09
    åĽŀé¦ĸ
    0.09
    éĢģç»Ļ
    0.08
    éĺľ
    0.08
     Deadline
    0.08
    äºĴéĢļ
    0.08
    çĵ´
    0.08
    orange
    0.08
    ä¸Ģç«Ļ
    0.08
    Activations Density 0.005%

    No Known Activations