© 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. 56866
    Prev
    Next
    INDEX
    Explanations

    luck and misfortune

    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
    游ä¹IJ
    -0.10
    çŀł
    -0.09
    çIJĨä¼ļ
    -0.09
    èĻ¹æ¡¥
    -0.09
    æĥĬ讶
    -0.09
    èĤĵ
    -0.09
    岸边
    -0.09
    ä¼ļéĢīæĭ©
    -0.08
    欣åĸľ
    -0.08
    ãĥĬãĥ«
    -0.08
    POSITIVE LOGITS
    好è¿IJ
    0.16
    è¯ħ
    0.15
    åIJī祥
    0.13
     unlucky
    0.13
    è¿IJåĬ¿
    0.13
    åIJīåĪ©
    0.13
     superst
    0.12
     curse
    0.12
    幸è¿IJ
    0.12
    é£İæ°´
    0.12
    Activations Density 0.079%

    No Known Activations