© 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. 11241
    Prev
    Next
    INDEX
    Explanations

    quality of life

    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
    è¢ħ
    -0.09
    pheric
    -0.09
    itable
    -0.09
    å¾Īæ¸ħæ¥ļ
    -0.09
    æĬ¥éħ¬
    -0.09
    ä¸ĢåĪĨ
    -0.09
    æĥħåķĨ
    -0.08
    è¿Ļå¥Ĺ
    -0.08
    å¤ĸæĿ¥
    -0.08
    Defs
    -0.08
    POSITIVE LOGITS
     life
    0.27
    çĶŁæ´»
    0.24
    çĶŁæ´»çļĦ
    0.23
     жизни
    0.22
     lives
    0.22
    life
    0.21
    _life
    0.21
    .life
    0.19
     Life
    0.18
     жизнÑĮ
    0.18
    Activations Density 0.127%

    No Known Activations