© 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. 5742
    Prev
    Next
    INDEX
    Explanations

    pleasure and enjoyment

    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
     squat
    -0.09
    airs
    -0.09
    /stretch
    -0.09
    大米
    -0.08
     Dun
    -0.08
    ?key
    -0.08
    ets
    -0.08
    æīĺ
    -0.08
    nonnull
    -0.08
    .ld
    -0.08
    POSITIVE LOGITS
     pleasure
    0.24
    ä¹IJ趣
    0.21
     plaisir
    0.21
    享åıĹ
    0.20
     pleasures
    0.19
    享
    0.18
     enjoyment
    0.18
    æĦīæĤ¦
    0.18
    å¿«ä¹IJ
    0.17
    çļĦä¹IJ趣
    0.17
    Activations Density 0.067%

    No Known Activations