© 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. 49257
    Prev
    Next
    INDEX
    Explanations

    clean water supply

    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
    身形
    -0.11
    è¡Įäºĭ
    -0.09
    æ¡£æ¡Ī
    -0.09
    æĺ§
    -0.09
    ãĥļãĥ³
    -0.08
    ç±³é¥Ń
    -0.08
    éľ²åĩº
    -0.08
     Whites
    -0.08
    åĨĴ
    -0.08
    å½¢
    -0.08
    POSITIVE LOGITS
    æ°´èµĦæºIJ
    0.12
    饮çĶ¨æ°´
    0.11
    æ±²
    0.11
    æ°´æºIJ
    0.11
    饮水
    0.11
    ä¾Ľæ°´
    0.10
    çŁ¿æ³īæ°´
    0.10
    æ°´éĩı
    0.10
    æ³īæ°´
    0.10
     drinking
    0.09
    Activations Density 0.048%

    No Known Activations