© 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. 6618
    Prev
    Next
    INDEX
    Explanations

    disease caused economic losses

    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
     lc
    -0.08
    æľį
    -0.08
    åľŁè±Ĩ
    -0.08
    è¥Ł
    -0.08
     gardening
    -0.08
    æŀľå®ŀ
    -0.08
    rag
    -0.08
    é£Ĵ
    -0.08
    .mit
    -0.08
    lc
    -0.08
    POSITIVE LOGITS
    è¹Ħ
    0.12
    åĨľä¸ļåĨľæĿij
    0.10
    èĥ´
    0.10
     slaughter
    0.10
    è¯Ħå®ļ
    0.10
    饲
    0.09
    è·Ĺ
    0.09
    äºĭåħĪ
    0.09
    è§Ħ模åĮĸ
    0.09
    ç¦ıåĪ©
    0.09
    Activations Density 0.509%

    No Known Activations