© 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. 6664
    Prev
    Next
    INDEX
    Explanations

    preclusion, estoppel, law of the case

    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
    stä
    -0.10
    çļĦæĪIJåĬŁ
    -0.09
    沫
    -0.09
    .cr
    -0.09
    èį£
    -0.09
    hog
    -0.09
    æĢ¥éľĢ
    -0.09
    TextChanged
    -0.09
    马åħĭ
    -0.08
    èİ«æĸ¯
    -0.08
    POSITIVE LOGITS
    æŶæķĪ
    0.12
    èĢ½è¯¯
    0.10
    追
    0.10
    æĶ¾è¿ĩ
    0.10
     statute
    0.09
    æ¶Ī
    0.09
     Memories
    0.08
    åĩłå¹´
    0.08
    elas
    0.08
    çĽ¥
    0.08
    Activations Density 0.216%

    No Known Activations