© 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. 49579
    Prev
    Next
    INDEX
    Explanations

    law, legislation, legal procedures

    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
    ripp
    -0.09
    éĵ¸
    -0.09
    åīįæľŁ
    -0.08
    Servi
    -0.08
     ÑĢай
    -0.08
    次
    -0.08
     projects
    -0.08
    annt
    -0.08
     THR
    -0.08
    otron
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.12
    æľīåħ³è§Ħå®ļ
    0.11
    å¿«æĿ¥
    0.11
    å®ĮåĸĦçļĦ
    0.11
    æĶ¾å®½
    0.10
    æ³ķå¾ĭ
    0.10
    æ³ķå¾ĭ责任
    0.10
    åĪ¶åº¦
    0.10
    ç«ĭæ³ķ
    0.10
    åĥµ
    0.10
    Activations Density 0.129%

    No Known Activations