© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29773
    Prev
    Next
    INDEX
    Explanations

    drinking water quality

    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
    ä¼Ĭæĭī
    -0.10
    åIJĥ饱
    -0.10
    èĸ°
    -0.09
    ä¸įåħ¬å¹³
    -0.09
    Exact
    -0.09
    .gs
    -0.09
    大使
    -0.09
    çĶŁäº§åĬĽ
    -0.09
    åIJ»
    -0.08
    è¿ĺ羣
    -0.08
    POSITIVE LOGITS
    æ°´è´¨
    0.12
    饮çĶ¨æ°´
    0.11
    æ°´æºIJ
    0.11
    æ°´ä¸Ń
    0.11
    饮çĶ¨
    0.11
    alg
    0.10
    çŁ¿æ³īæ°´
    0.10
    饮水
    0.10
    éľīç´ł
    0.09
    åĽ½åĢº
    0.09
    Activations Density 0.079%

    No Known Activations