© 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. 21091
    Prev
    Next
    INDEX
    Explanations

    urinary tract conditions

    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
    bars
    -0.10
    缴è¾ĸ
    -0.09
    äº®çĽ¸
    -0.09
     ÑĥвеÑĢ
    -0.09
    æŀģéĢŁ
    -0.09
    è¸ħ
    -0.09
    ảng
    -0.09
    ç§Ģ丽
    -0.09
     Ramp
    -0.09
    ä¸ĢæĶ¯
    -0.09
    POSITIVE LOGITS
    åİķæīĢ
    0.15
    å°¿
    0.15
    马桶
    0.14
    ãĥĪãĤ¤ãĥ¬
    0.13
    åİķ
    0.13
     urinary
    0.12
     urine
    0.12
     bladder
    0.12
    å±ģèĤ¡
    0.12
    粪
    0.11
    Activations Density 0.324%

    No Known Activations