© 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. 53816
    Prev
    Next
    INDEX
    Explanations

    people and their roles

    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
    _pan
    -0.10
     pan
    -0.09
     Funeral
    -0.09
     позв
    -0.09
     Pan
    -0.09
    æ³Ľ
    -0.08
     cuckold
    -0.08
    sis
    -0.08
    åŃ©åŃIJ们
    -0.08
    æĢµ
    -0.08
    POSITIVE LOGITS
    è¿Ļä½į
    0.18
    å¹´è½»çļĦ
    0.12
    å¤§åĽ½
    0.11
    éĵ®
    0.10
    è¾
    0.10
    è¿Ļæł·ä¸Ģ个
    0.10
    å·¨æĺŁ
    0.10
    å¿ĥ缮
    0.10
    è¿ĻåIJį
    0.10
    ä¼Łå¤§çļĦ
    0.10
    Activations Density 0.087%

    No Known Activations