© 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. 57602
    Prev
    Next
    INDEX
    Explanations

    living with others

    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
    æ¥ļ
    -0.09
    :[[
    -0.09
    aldo
    -0.09
    解å¼Ģ
    -0.09
    æŁĶæĢ§
    -0.08
    ç§ĥ
    -0.08
     Empire
    -0.08
    ocy
    -0.08
    æĭľ
    -0.08
    oge
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»çļĦ
    0.17
    çĶŁæ´»
    0.16
    æļ®ãĤīãģĹ
    0.15
    å±ħä½ı
    0.14
     living
    0.13
    æļ®ãĤī
    0.13
    çĶŁæ´»æĸ¹å¼ı
    0.13
    çĶŁæ´»åľ¨
    0.13
    ä½ıåľ¨
    0.13
    living
    0.12
    Activations Density 0.129%

    No Known Activations