© 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. 54912
    Prev
    Next
    INDEX
    Explanations

    support, tutorials, and services

    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
    å¯Ĵåģĩ
    -0.10
    anke
    -0.10
    å¥ł
    -0.09
     xuyên
    -0.09
    æĻ®æ³ķ
    -0.09
    åħ¬ç«ĭ
    -0.09
     giãn
    -0.09
    кÑĢа
    -0.09
    _HDR
    -0.09
    .lesson
    -0.09
    POSITIVE LOGITS
    çıįæĥľ
    0.10
    帮æī¶
    0.09
     Lans
    0.09
     ка
    0.09
    ICES
    0.09
    ials
    0.09
    arium
    0.08
     Improvement
    0.08
    æľĭ
    0.08
     remed
    0.08
    Activations Density 0.050%

    No Known Activations