© 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. 1104
    Prev
    Next
    INDEX
    Explanations

    sole and foot parts

    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
    illis
    -0.09
    æĿ¥æºIJäºİ
    -0.09
    åĿª
    -0.09
    chy
    -0.09
    -ending
    -0.08
    éĢŀ
    -0.08
    夷
    -0.08
    æĪIJ交
    -0.08
    ensions
    -0.08
    postcode
    -0.08
    POSITIVE LOGITS
    éĢıæ°Ķ
    0.10
    .hs
    0.09
    ä¸ŃåİŁ
    0.09
    úa
    0.09
    нÑıÑĤ
    0.09
    VED
    0.09
    arter
    0.08
     паÑĢÑĤи
    0.08
    brain
    0.08
    æľĭåıĭ
    0.08
    Activations Density 0.005%

    No Known Activations