© 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. 58933
    Prev
    Next
    INDEX
    Explanations

    lucky and fortunate

    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
    éĩijåĪļ
    -0.08
    spot
    -0.08
    ulet
    -0.08
    åīį线
    -0.08
    大çIJĨçŁ³
    -0.08
    æ¶Īè´¹éľĢæ±Ĥ
    -0.08
    aison
    -0.08
    ä¸įéĢĤ
    -0.08
     frontier
    -0.08
    éĿ
    -0.08
    POSITIVE LOGITS
    幸è¿IJ
    0.32
     lucky
    0.24
     fortunate
    0.21
    èį£å¹¸
    0.19
    æľī幸
    0.19
    幸
    0.18
    åºĨ幸
    0.18
     luck
    0.18
     Lucky
    0.17
    è¿IJæ°Ķ
    0.17
    Activations Density 0.044%

    No Known Activations