© 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. 35230
    Prev
    Next
    INDEX
    Explanations

    attractiveness, charm, appeal

    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
    éľĵ
    -0.10
    ç¿Ķ
    -0.10
    æ¯Ĺ
    -0.09
     Enabled
    -0.09
    éŁŃ
    -0.08
    æģ¨
    -0.08
    æ¿Ĵ
    -0.08
    éħ¢
    -0.08
    å¾ĹæĦı
    -0.08
    é³
    -0.08
    POSITIVE LOGITS
    éŃħåĬĽ
    0.28
    åIJ¸å¼ķåĬĽ
    0.22
    çļĦéŃħåĬĽ
    0.21
     appeal
    0.18
     charm
    0.18
     allure
    0.17
    诱æĥij
    0.16
    åIJ¸å¼ķ
    0.16
    åIJ¸å¼ķäºĨ
    0.16
     charms
    0.15
    Activations Density 0.057%

    No Known Activations