© 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. 27268
    Prev
    Next
    INDEX
    Explanations

    enemies, foes, allies, rivals, neighbours

    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
    ä»Ģä¹Īäºĭ
    -0.11
    éľĩæĴ¼
    -0.09
    æĸ½å±ķ
    -0.09
    宽
    -0.09
    æѤ类
    -0.09
    èĮĥæĸĩ
    -0.09
    é¢ľ
    -0.09
    ëijĺ
    -0.09
    æĻ®éĢļ人
    -0.09
    mite
    -0.09
    POSITIVE LOGITS
    æķĮ人
    0.21
    åIJĪä½ľä¼Ļä¼´
    0.16
     enemies
    0.16
    æķĮ
    0.16
    对æīĭ
    0.15
    æķµ
    0.14
     enemy
    0.14
     foes
    0.13
    ä¼Ļä¼´
    0.13
     allies
    0.13
    Activations Density 0.098%

    No Known Activations