© 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. 53628
    Prev
    Next
    INDEX
    Explanations

    Norma Desmond, article, session, stated

    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
    ç¥ŀæĥħ
    -0.10
    æĮ¨
    -0.09
    è¿Ļå¼ł
    -0.09
    åħ¨æĻ¯
    -0.09
    èį¯ä¸ļ
    -0.09
    åĬ©
    -0.09
     пÑĥÑĤ
    -0.09
     populous
    -0.09
    æķ£åıij
    -0.08
    æĭĵå±ķ
    -0.08
    POSITIVE LOGITS
    ä¸İæŶ
    0.10
    enus
    0.09
    漪
    0.08
    éķ¿çŁŃ
    0.08
    åħļ
    0.08
    عد
    0.08
    ahr
    0.08
     Super
    0.08
    äºĮæīĭ
    0.08
    éªIJ
    0.08
    Activations Density 0.001%

    No Known Activations