© 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. 31992
    Prev
    Next
    INDEX
    Explanations

    medical and technical fields

    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
    æĪijæĺ¯
    -0.08
    éĶ¯
    -0.08
     plagiar
    -0.08
    าม
    -0.08
    æľĶ
    -0.08
    è¿ĻéĩĮæĺ¯
    -0.08
    è¾ĺ
    -0.08
    æģ¨ä¸įå¾Ĺ
    -0.08
    ipo
    -0.08
    åįģå¹´åīį
    -0.08
    POSITIVE LOGITS
    åı²ä¸Ĭ
    0.11
    ä¸ŃæľĢ
    0.10
    nox
    0.09
    Ĭ
    0.09
    .Pixel
    0.08
    çŀŃ
    0.08
    åİĨåı²ä¸Ĭ
    0.08
    smith
    0.08
    å°±æѤ
    0.08
    RIX
    0.08
    Activations Density 1.412%

    No Known Activations