© 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. 20054
    Prev
    Next
    INDEX
    Explanations

    water and sewer infrastructure

    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
    å¼ĢèĬ±
    -0.09
    羶
    -0.09
    æĮijéĢī
    -0.09
    çĺŁ
    -0.09
    è¾Ķ
    -0.09
    æīĵæŃ»
    -0.09
    秧
    -0.09
    æ¯ģçģŃ
    -0.09
    OPSIS
    -0.09
     Mountains
    -0.09
    POSITIVE LOGITS
    æİĴæ°´
    0.13
    污水
    0.10
    æ³»
    0.09
     unm
    0.09
    èĬ±åĽŃ
    0.09
    åŁİ管
    0.09
    æİĴ污
    0.08
    窨
    0.08
    容éĩı
    0.08
    ãĤ·ãĤ¹ãĥĨãĥł
    0.08
    Activations Density 0.054%

    No Known Activations