© 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. 21445
    Prev
    Next
    INDEX
    Explanations

    UCI, FIFA, World Cup

    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
    æĺ¯åĽ½åĨħ
    -0.12
    _EOF
    -0.11
    æĺ¯æĪijåĽ½
    -0.10
    缮åīįåĽ½åĨħ
    -0.10
    éļıæīĭ
    -0.09
    å·¡èĪª
    -0.09
    ä¸ĢåłĨ
    -0.09
    æĪIJ为ä¸ŃåĽ½
    -0.09
    odem
    -0.08
    人人
    -0.08
    POSITIVE LOGITS
     kang
    0.11
    åľ¨åħ¨çIJĥ
    0.10
    è·¨åĽ½
    0.09
     pumping
    0.09
    çĤ¹å¤´
    0.09
    èĤļ
    0.09
    ixon
    0.09
    大象
    0.08
     BigInt
    0.08
    .nom
    0.08
    Activations Density 0.101%

    No Known Activations