© 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. 27436
    Prev
    Next
    INDEX
    Explanations

    football or footprints

    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
    çļĦ缮åħī
    -0.10
    ornings
    -0.10
    urat
    -0.09
    åIJĮä¼´
    -0.09
    çļĦçľ¼åħī
    -0.09
    çļĦçľ¼ç¥ŀ
    -0.08
     اÙĦÙĥبرÙī
    -0.08
     hosp
    -0.08
    sic
    -0.08
    .forward
    -0.08
    POSITIVE LOGITS
    bridge
    0.11
    趾
    0.10
    foot
    0.10
    à¹ģà¸Ĭ
    0.10
    prints
    0.09
    ery
    0.09
    COND
    0.09
    fall
    0.09
    踣
    0.09
    æĤ¼
    0.09
    Activations Density 0.024%

    No Known Activations