© 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. 34922
    Prev
    Next
    INDEX
    Explanations

    outpatient clinics

    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
    æŀķ头
    -0.10
    èĩ´åij½
    -0.09
    æĹħ
    -0.09
    天èĬ±
    -0.09
    åIJ¦
    -0.09
    ç¼Ł
    -0.09
    å²Ń
    -0.09
    zw
    -0.08
    天ä¸Ĭ
    -0.08
    æĹħé¦Ĩ
    -0.08
    POSITIVE LOGITS
     appointments
    0.10
    4
    0.10
    6
    0.10
    7
    0.10
    åij¨äºĶ
    0.09
    0
    0.09
    5
    0.09
    3
    0.09
     visit
    0.09
    å°±è¯Ĭ
    0.09
    Activations Density 0.205%

    No Known Activations