© 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. 11540
    Prev
    Next
    INDEX
    Explanations

    creation and building

    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
    _cos
    -0.09
    对æĪij们
    -0.09
    çݯ氧
    -0.09
    _exc
    -0.09
    ÙĪات
    -0.09
    çļĦåķĨåĵģ
    -0.08
    æĿijå¹²éĥ¨
    -0.08
    åĽ½åľŁèµĦæºIJ
    -0.08
    对ä¼ģä¸ļ
    -0.08
    æĬ¬å¤´
    -0.08
    POSITIVE LOGITS
    çłĶ究ä¸Ńå¿ĥ
    0.13
    ä¸Ģ座
    0.11
    èµ·äºĨ
    0.11
    ä¸ĢæīĢ
    0.11
    ä¸ĵéŨ
    0.10
     facilities
    0.10
    辦
    0.10
    纪念é¦Ĩ
    0.09
    ä¸Ģ个æĸ°çļĦ
    0.09
    ä¼ijæģ¯
    0.09
    Activations Density 0.132%

    No Known Activations