© 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. 39737
    Prev
    Next
    INDEX
    Explanations

    competition and rivalry

    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
    æŀ¯
    -0.10
     Rae
    -0.09
    ucher
    -0.09
    çĮ¥
    -0.08
    åīįçŀ»
    -0.08
    hands
    -0.08
    å¤Ń
    -0.08
    rex
    -0.08
    åĩ¯
    -0.08
    æ»Ķ
    -0.08
    POSITIVE LOGITS
    ç«ŀäºī
    0.19
     competition
    0.17
    ç«ŀèµĽ
    0.16
    æ¿ĢçĥĪçļĦ
    0.15
    äºī
    0.15
    競çĪŃ
    0.15
    çļĦç«ŀäºī
    0.15
    æ¿ĢçĥĪ
    0.14
    å¸Ĥåľºç«ŀäºī
    0.14
     rivalry
    0.14
    Activations Density 0.071%

    No Known Activations