© 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. 56245
    Prev
    Next
    INDEX
    Explanations

    medical terms and acronyms

    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
     обоÑĢ
    -0.09
    渴
    -0.09
    å¥Ĺ
    -0.09
    çĵ·
    -0.09
    Apis
    -0.09
    repid
    -0.09
    æĴŀ
    -0.08
    wares
    -0.08
    rang
    -0.08
    _CY
    -0.08
    POSITIVE LOGITS
    éĢļé£İ
    0.10
    å¾ĹäºĨ
    0.09
     vent
    0.09
     DEA
    0.09
     ind
    0.08
    ä¸Ģè´¯
    0.08
    éĢĥ离
    0.08
    inds
    0.08
    åįİåįĹ
    0.08
    è´¨éĩıå®īåħ¨
    0.08
    Activations Density 0.147%

    No Known Activations