© 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. 5118
    Prev
    Next
    INDEX
    Explanations

    men and women

    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
    MET
    -0.10
    ç´¢åıĸ
    -0.10
    妹
    -0.10
    rek
    -0.09
    åĴ«
    -0.09
    æģ¯
    -0.09
    èµĦ
    -0.09
    lien
    -0.09
    人家
    -0.08
    èħ´
    -0.08
    POSITIVE LOGITS
    ä¸ĢæŶ
    0.09
    ä¸ĢçĤ¹
    0.09
    ahu
    0.09
    åĽłä¸ºä»ĸ们
    0.08
    åĭ¿
    0.08
    iores
    0.08
    æĽĪ
    0.08
    Ath
    0.08
    åĽłä¸ºå®ĥ
    0.08
    æ¯ħ
    0.08
    Activations Density 0.232%

    No Known Activations