© 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. 54540
    Prev
    Next
    INDEX
    Explanations

    get, gets, got, gotten

    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
    åīįä¸ĸ
    -0.10
    æľºä¼ļ
    -0.10
    æľīæľºä¼ļ
    -0.09
     cow
    -0.09
    å·Ŀ
    -0.09
    ORB
    -0.09
    å¼Ħ
    -0.09
    èĤł
    -0.09
    perl
    -0.09
    amt
    -0.09
    POSITIVE LOGITS
    ocup
    0.11
    å¼¥
    0.10
    ç´¯äºĨ
    0.10
    otide
    0.09
    oder
    0.09
    tings
    0.08
    å¾Īéĩįè¦ģ
    0.08
    è¶ĬæĿ¥è¶Ĭ好
    0.08
    满äºĨ
    0.08
    è¿ĻåIJį
    0.08
    Activations Density 0.021%

    No Known Activations