© 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. 48860
    Prev
    Next
    INDEX
    Explanations

    gynecology

    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
    æŶæĬ¥
    -0.10
    æĸ°åĬł
    -0.09
    åIJı
    -0.09
    ä¼ı
    -0.09
    表çĻ½
    -0.09
    为ä¼ģä¸ļ
    -0.09
    ulen
    -0.09
    éŀł
    -0.09
    \Table
    -0.09
    æĢ§ä»·
    -0.08
    POSITIVE LOGITS
    饶
    0.10
    ippy
    0.09
    andle
    0.09
     Counties
    0.08
    tered
    0.08
    æµ·ä¸Ĭ
    0.08
     reverted
    0.08
     Pron
    0.08
    hn
    0.07
     revert
    0.07
    Activations Density 0.011%

    No Known Activations