© 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. 5203
    Prev
    Next
    INDEX
    Explanations

    State Department email

    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
    çıł
    -0.09
    ÑİÑĢ
    -0.09
    æľīèĩªå·±çļĦ
    -0.09
    çĬĢ
    -0.09
    éĴĪ
    -0.09
    çĦľ
    -0.09
    åIJĮä¸ļ
    -0.08
    buster
    -0.08
    éĥ½æľīèĩªå·±
    -0.08
    å¼Ģåĩº
    -0.08
    POSITIVE LOGITS
    iful
    0.10
    身å¿ĥåģ¥åº·
    0.09
    rit
    0.09
    礼仪
    0.08
    adh
    0.08
    宿
    0.08
    身å¿ĥ
    0.08
    éĤ¸
    0.08
    holes
    0.08
    éĹ»åIJį
    0.08
    Activations Density 0.195%

    No Known Activations