© 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. 18348
    Prev
    Next
    INDEX
    Explanations

    either/or choices

    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
    强è°ĥ
    -0.08
    宪
    -0.08
    richt
    -0.08
    ä¸ŃåĽ½åĽ½éĻħ
    -0.08
    azar
    -0.08
    秩
    -0.08
    éķŀ
    -0.08
    chi
    -0.08
    bus
    -0.08
    æĺ¯ä¸Ģ座
    -0.08
    POSITIVE LOGITS
    éĹ´æİ¥
    0.16
    缴æİ¥
    0.13
     direct
    0.12
     via
    0.11
    éĢļè¿ĩ
    0.11
    via
    0.11
     indirect
    0.10
     overt
    0.10
    ä¸įç»ıæĦı
    0.10
     through
    0.10
    Activations Density 0.091%

    No Known Activations