© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20489
    Prev
    Next
    INDEX
    Explanations

    drug names and medical treatments

    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
    ä¹ĭå®¶
    -0.10
    æ¿ĢçĥĪçļĦ
    -0.09
    竣çĦ¶
    -0.09
    rô
    -0.08
     arsch
    -0.08
    çĸ¥
    -0.08
    å®Ŀè´µ
    -0.08
    积水
    -0.08
    spl
    -0.08
    llum
    -0.08
    POSITIVE LOGITS
     ÑģейÑĩаÑģ
    0.08
    æĬ¤
    0.08
    ordion
    0.08
    欣
    0.08
     consort
    0.08
    guard
    0.08
    æĪĺçķ¥æĢ§
    0.08
    丰ç¡ķ
    0.07
    èıģ
    0.07
    -sort
    0.07
    Activations Density 0.550%

    No Known Activations