© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37030
    Prev
    Next
    INDEX
    Explanations

    market direction and price changes

    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
    åħī彩
    -0.11
    å¬Ĺ
    -0.09
    èĢĢ
    -0.09
    éĺģ
    -0.08
    æ¿ł
    -0.08
    æ¸ħåĩī
    -0.08
    æĪ¾
    -0.08
    aign
    -0.08
    æµ´
    -0.08
    çĮ®è¡Ģ
    -0.08
    POSITIVE LOGITS
    主线
    0.12
    åĥ®
    0.10
    åıįå¼¹
    0.09
    èĩ³ä¸Ĭ
    0.09
    æĭīåįĩ
    0.09
    åħ¬ä¸»
    0.09
    æĪIJ交éĩı
    0.09
    æĭ¾
    0.09
    æŀĦçŃij
    0.08
    主åĬĽ
    0.08
    Activations Density 0.042%

    No Known Activations