© 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. 31325
    Prev
    Next
    INDEX
    Explanations

    lists of names or descriptions

    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
    ä¸įäºĨ
    -0.10
    æĺ¯ä¸Ģ件
    -0.10
    ä¸Ģ个个
    -0.09
    ä¸įä¸Ĭ
    -0.09
    æĺ¯ä¸Ģ项
    -0.09
    è¿Ļ群
    -0.09
    ndon
    -0.09
    rait
    -0.09
    éģį
    -0.08
    gist
    -0.08
    POSITIVE LOGITS
    åķ¤
    0.11
    åįıä¼ļä¼ļåijĺ
    0.10
    åIJĪæł¼
    0.09
    ä»ĸä¹Ł
    0.09
    磶
    0.09
    ì°°
    0.09
    ä»ĸæĽ¾
    0.09
    羣æŃ£åģļåĪ°
    0.09
    éĽ¶é£Ł
    0.09
    ооÑĢ
    0.09
    Activations Density 0.098%

    No Known Activations