© 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. 47898
    Prev
    Next
    INDEX
    Explanations

    rivalry and enemies

    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
    溢
    -0.11
    èĽĽ
    -0.10
    æĿŁ
    -0.09
    éĢĢåĩº
    -0.09
    YS
    -0.08
     Gems
    -0.08
     PS
    -0.08
    ussed
    -0.08
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.08
    ç½ijç»ľä¼łæĴŃ
    -0.08
    POSITIVE LOGITS
    ä»ĩ
    0.19
    鼳
    0.15
    æķĮ
    0.14
    对ç«ĭ
    0.14
     rival
    0.14
     rivals
    0.14
    æķµ
    0.13
     opposing
    0.12
    对æīĭ
    0.12
    æķĮ人
    0.12
    Activations Density 0.086%

    No Known Activations