© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9171
    Prev
    Next
    INDEX
    Explanations

    up to

    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
    ãĥ³
    -0.09
    _Word
    -0.09
    et
    -0.09
    æķ¬
    -0.09
     budding
    -0.08
    å¹´å¤ľ
    -0.08
    æĥ³èµ·æĿ¥
    -0.08
    ÑĢаÐ
    -0.08
    ä¸įè¦ģ太
    -0.08
    dsp
    -0.08
    POSITIVE LOGITS
    社ä¼ļåĮĸ
    0.11
    æĮĸæİĺ
    0.09
    åŀĤ
    0.09
    ä¸įéĶĻ
    0.09
    caught
    0.08
    구
    0.08
    åľ¨èģĮ
    0.08
    èijĹ
    0.08
    寻
    0.08
    äºĽ
    0.08
    Activations Density 0.006%

    No Known Activations