© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21158
    Prev
    Next
    INDEX
    Explanations

    medical suffixes ending in ard or itis

    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
    ÑĤик
    -0.09
    æŃ£çīĪ
    -0.09
    空
    -0.09
    对èĩªå·±
    -0.09
    ä¸ĭåįĬ
    -0.08
     Dahl
    -0.08
    Ñĩив
    -0.08
    æ½¢
    -0.08
    ormal
    -0.08
    èħ¥
    -0.08
    POSITIVE LOGITS
    æ³Ľ
    0.09
    æĥ³è±¡åĬĽ
    0.09
    idad
    0.08
    :date
    0.08
     Redistributions
    0.08
    ally
    0.08
    æİ°
    0.08
     Kỳ
    0.08
    ERO
    0.08
    BERS
    0.08
    Activations Density 0.017%

    No Known Activations