© 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. 55566
    Prev
    Next
    INDEX
    Explanations

    cooking ingredients

    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
    河水
    -0.11
    éĤ£ä¸ªäºº
    -0.11
     Graz
    -0.09
    弩
    -0.09
    oplevel
    -0.09
    ä¸Ģ头
    -0.09
    astle
    -0.09
    ä¸ŃåĽ½æĶ¿åºľ
    -0.09
    èħĮ
    -0.08
    Terminal
    -0.08
    POSITIVE LOGITS
    oin
    0.09
    ia
    0.09
    éĢµ
    0.09
    åĮĹéĥ¨
    0.08
     Chu
    0.08
     onFailure
    0.08
    OLS
    0.08
    亶
    0.08
    mour
    0.08
     ob
    0.08
    Activations Density 0.017%

    No Known Activations