© 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. 57394
    Prev
    Next
    INDEX
    Explanations

    bath, shower, tub

    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
    é»İæĺİ
    -0.10
    纥
    -0.10
    è¿ľæĸ¹
    -0.09
    ä»Ģä¹ĪåİŁåĽł
    -0.09
    æĻ´
    -0.09
    éĤ£ä¹Ī容æĺĵ
    -0.09
    /layouts
    -0.09
    è´²
    -0.09
    ntl
    -0.09
    ergy
    -0.09
    POSITIVE LOGITS
    澡
    0.16
    æ´Ĺ澡
    0.14
    æµ´
    0.13
     baths
    0.12
    æ²IJæµ´
    0.11
    浴室
    0.11
    身åŃIJ
    0.10
    æĭ¨
    0.10
     bath
    0.10
     water
    0.10
    Activations Density 0.020%

    No Known Activations