© 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. 32111
    Prev
    Next
    INDEX
    Explanations

    gallbladder, bile, cholesterol

    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
    éĺħ读åħ¨æĸĩ
    -0.09
    举æĬ¥çĶµè¯Ŀ
    -0.09
    ural
    -0.09
     Barcl
    -0.09
    ##_
    -0.08
     Gilles
    -0.08
    äºĨèĩªå·±çļĦ
    -0.08
    ãĤ¢ãĤ¦ãĥĪ
    -0.08
    ABEL
    -0.08
    æľĿ
    -0.08
    POSITIVE LOGITS
    à¹ģà¸Ĺ
    0.11
     обÑĢазом
    0.09
    atile
    0.09
     visceral
    0.09
    nost
    0.08
    çıĢ
    0.08
    åĽĬ
    0.08
    _SWAP
    0.08
    以人为
    0.08
    urst
    0.08
    Activations Density 0.054%

    No Known Activations