© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35986
    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
    hm
    -0.10
    erde
    -0.09
    gages
    -0.08
    åľ¨ä¸Ģèµ·
    -0.08
    ewood
    -0.08
    åĽ½ç«ĭ
    -0.08
    æĭ¿åĩº
    -0.08
    ä½Ĩä¸įéĻIJ
    -0.08
     nett
    -0.08
    äºĨä»ĸçļĦ
    -0.08
    POSITIVE LOGITS
    /or
    0.10
    ä¹Łä¸įè¦ģ
    0.10
    lea
    0.09
    æĪijä»¬ä¹Ł
    0.09
    çļĦç»ıåħ¸
    0.08
    ä¹Łä¸įæĺ¯
    0.08
    å¦Ĥæŀľè¯´
    0.08
    ä¹ĺ客
    0.08
    usted
    0.08
    egra
    0.08
    Activations Density 0.409%

    No Known Activations