© 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. 63098
    Prev
    Next
    INDEX
    Explanations

    daily cares and stress

    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
    æľĢ好ä¸įè¦ģ
    -0.10
    èѬ
    -0.10
    èĢĮéĿŀ
    -0.10
    尤为éĩįè¦ģ
    -0.09
    没éĶĻ
    -0.09
    ä¸įæĪIJ
    -0.09
    æ²±
    -0.09
    æIJ¬è¿IJ
    -0.09
    çļĦç»ıåħ¸
    -0.09
    éĤ®å¯Ħ
    -0.09
    POSITIVE LOGITS
    åĸ§
    0.13
    纷
    0.10
    æĸ¤
    0.09
    åĮ¡
    0.09
    too
    0.09
     too
    0.09
    太è¿ĩ
    0.09
    çĶŁæ´»çļĦ
    0.08
     Too
    0.08
    spam
    0.08
    Activations Density 0.048%

    No Known Activations