© 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. 26570
    Prev
    Next
    INDEX
    Explanations

    court proceedings and appearances

    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
    追
    -0.10
    åıijå±ķä¸Ń
    -0.09
    为主çļĦ
    -0.09
    CB
    -0.09
    TER
    -0.08
    ä¸ĸçķĮåIJĦåĽ½
    -0.08
    åħ®
    -0.08
    ä¸ĢçĤ¹ä¹Łä¸į
    -0.08
    zw
    -0.08
     CB
    -0.08
    POSITIVE LOGITS
    -Pacific
    0.10
    ä¸ĢæĹı
    0.09
    urd
    0.08
    æŃ£å½ĵ
    0.08
    è¦ģä¹Ī
    0.08
     Redistribution
    0.08
    å·§
    0.08
    åı°éĺ¶
    0.08
    timeofday
    0.08
    neau
    0.08
    Activations Density 0.006%

    No Known Activations