© 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. 34067
    Prev
    Next
    INDEX
    Explanations

    female sexuality, strength, life, sentiment

    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
    æĮĸæİĺ
    -0.09
    ocal
    -0.08
    ãģĶãģĸãģĦãģ¾ãģĻ
    -0.08
    严éĩįå½±åĵį
    -0.08
    ongan
    -0.08
    ä¸īæľŁ
    -0.08
    滢
    -0.08
     outright
    -0.08
    称ä¹ĭ
    -0.08
    æ¶ķ
    -0.08
    POSITIVE LOGITS
    ä¹ĭæĦı
    0.10
    æĹºçĽĽ
    0.09
    ä¹Łå¸ĮæľĽ
    0.09
    离ä¸įå¼Ģ
    0.09
    дÑĢ
    0.09
    agen
    0.09
    åıĪè¦ģ
    0.09
    æĨ©
    0.08
    ä¸Ģæł·
    0.08
     обо
    0.08
    Activations Density 0.083%

    No Known Activations