© 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. 17601
    Prev
    Next
    INDEX
    Explanations

    energy, transport, mental, digital, fabrics, food

    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
     Lets
    -0.09
    èĢĮä¸į
    -0.08
    æľ¬èĥ½
    -0.08
    鹦
    -0.08
     mcc
    -0.08
    èĦĶ
    -0.08
    /vendor
    -0.08
    arris
    -0.08
    ilm
    -0.08
    娲
    -0.08
    POSITIVE LOGITS
    产åѦ
    0.09
    æĢ¥éľĢ
    0.09
     meille
    0.09
    çłĶ究
    0.09
    çĤķ
    0.09
    çļĦçłĶ究
    0.08
    лÑĥÑĩ
    0.08
    ordes
    0.08
    åIJįå¸Ī
    0.08
    topics
    0.08
    Activations Density 0.308%

    No Known Activations