© 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. 17488
    Prev
    Next
    INDEX
    Explanations

    UN or United Nations entities

    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
    ustin
    -0.09
    ней
    -0.09
    ä¸ĩåĪĨ
    -0.09
    ảnh
    -0.09
    èİ«è¿ĩäºİ
    -0.09
    èĥ¤
    -0.09
    nts
    -0.09
    abouts
    -0.09
    å»Ľ
    -0.08
     latter
    -0.08
    POSITIVE LOGITS
    iswa
    0.11
    سÙģ
    0.10
    çĦ¶æĺ¯
    0.09
    ÂŃ
    0.09
    opoly
    0.09
    o
    0.09
    æĢł
    0.09
    rade
    0.08
    umber
    0.08
    ormal
    0.08
    Activations Density 0.010%

    No Known Activations