© 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. 9725
    Prev
    Next
    INDEX
    Explanations

    no idea

    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
    大家éĥ½åľ¨
    -0.12
    æľīä¸ĢäºĽ
    -0.10
    æľīä¸Ģå®ļçļĦ
    -0.10
    ä»ħä¾ĽåıĤèĢĥ
    -0.09
    大家éĥ½
    -0.09
    çļĦæŃ¥ä¼IJ
    -0.09
    çļĦä¸ĢäºĽ
    -0.09
    uster
    -0.09
    çĽĪ
    -0.09
    çļĦä¸Ģç§į
    -0.09
    POSITIVE LOGITS
     дело
    0.10
    å£ģ
    0.10
    æĥ§
    0.09
    lessly
    0.09
    THING
    0.09
    าย
    0.09
    èĥ½åĬĽåĴĮ
    0.09
    adan
    0.09
    arend
    0.08
    fully
    0.08
    Activations Density 0.019%

    No Known Activations