© 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. 23242
    Prev
    Next
    INDEX
    Explanations

    diaper

    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
    å¼ĢéĺĶ
    -0.09
     Barton
    -0.08
     Yates
    -0.08
    artin
    -0.08
    arton
    -0.08
    ryo
    -0.08
    .getInfo
    -0.08
    _ins
    -0.08
     Jasmine
    -0.08
    æ¯ıä¸Ģ个人
    -0.08
    POSITIVE LOGITS
    ä¸Ģæŀļ
    0.10
    ped
    0.10
    åĵŃæ³£
    0.10
    裤åŃIJ
    0.09
    æŀļ
    0.09
    éĢĢå¸Ĥ
    0.09
    èŁĨ
    0.09
    峪
    0.09
    åºĬ
    0.09
    å´©
    0.09
    Activations Density 0.185%

    No Known Activations