© 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. 10194
    Prev
    Next
    INDEX
    Explanations

    luck, fortunate, easy, much

    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¸Ģ个å¤ļ
    -0.09
    æ©IJ
    -0.09
    attempt
    -0.09
     SCO
    -0.09
     attempt
    -0.09
    è¯ķåĽ¾
    -0.08
    ç²¾å¯Ĩ
    -0.08
    çIJ®
    -0.08
    äºĨ解ä¸Ģä¸ĭ
    -0.08
    å°Ŀè¯ķ
    -0.08
    POSITIVE LOGITS
     luck
    0.14
    è¿IJæ°Ķ
    0.14
    幸è¿IJ
    0.14
    侥幸
    0.12
     lucky
    0.12
    Luck
    0.12
    åģ¶çĦ¶
    0.11
    å¾ĹçĽĬäºİ
    0.11
    à¹Ĥà¸Ĭà¸Ħ
    0.11
     fortunate
    0.11
    Activations Density 0.118%

    No Known Activations