© 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. 56035
    Prev
    Next
    INDEX
    Explanations

    emoticon punctuation

    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
     Sterling
    -0.08
    éªł
    -0.08
    Intl
    -0.08
    éĥIJ
    -0.08
    ibu
    -0.08
    éľľ
    -0.08
    åĹĿ
    -0.07
     Pie
    -0.07
    æĿĥ
    -0.07
    pos
    -0.07
    POSITIVE LOGITS
    åīį身
    0.10
    è¾Ī
    0.10
    æĥĨ
    0.10
    è¹Ļ
    0.09
    èĭ¥æĤ¨
    0.09
    两åIJį
    0.09
    èĢģ人家
    0.09
    èººåľ¨åºĬä¸Ĭ
    0.09
    累累
    0.09
    ä¸ĩä¸Ģ
    0.09
    Activations Density 0.064%

    No Known Activations