© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52717
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    ãĤıãĤĬ
    -0.10
    毳
    -0.10
     Arn
    -0.10
    åŁİå¸Ĥåıijå±ķ
    -0.09
    icode
    -0.09
    icus
    -0.09
    尾巴
    -0.09
    çĻ½ç³ĸ
    -0.09
    æĬµæĬĹåĬĽ
    -0.09
    orate
    -0.09
    POSITIVE LOGITS
    yro
    0.09
    宥
    0.09
     Clarence
    0.09
     soc
    0.09
    ç«ŀ
    0.09
    aurus
    0.09
     slack
    0.08
    å¯ĮåIJ«
    0.08
    soc
    0.08
    çķª
    0.08
    Activations Density 0.025%

    No Known Activations