© 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. 58645
    Prev
    Next
    INDEX
    Explanations

    Justice and law terms

    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
    åŃIJéĩĮ
    -0.14
    sWith
    -0.11
    ers
    -0.11
    å¹ħ度
    -0.10
    ulario
    -0.10
    à¸Ļาà¸Ļ
    -0.10
    ç»´å¥ĩ
    -0.09
    æľĢç¾İ
    -0.09
    å®ĺåı¸
    -0.09
    工夫
    -0.09
    POSITIVE LOGITS
    ariat
    0.10
    FUL
    0.10
    fully
    0.10
    اء
    0.10
    éķ¯
    0.10
    omo
    0.10
    大èĩ£
    0.09
    ably
    0.09
    owie
    0.09
    SHIP
    0.09
    Activations Density 0.157%

    No Known Activations