© 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. 8335
    Prev
    Next
    INDEX
    Explanations

    Romeo and Juliet

    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
    lamp
    -0.10
    ly
    -0.09
    iac
    -0.08
    å½ĵä»ĸ
    -0.08
    级以ä¸Ĭ
    -0.08
    رÙģ
    -0.08
    累累
    -0.08
    uries
    -0.08
    åģļ大
    -0.08
    nock
    -0.08
    POSITIVE LOGITS
    éĽī
    0.10
    stride
    0.10
    ãĤ¤ãĥ©
    0.09
    è¯Ľ
    0.09
    骥
    0.09
    ä¸ĢåĽŀäºĭ
    0.09
    å½Ģ
    0.09
    éĢĤåIJĪèĩªå·±
    0.09
    ä¸Ģç»Ħ
    0.09
    âĹĪ
    0.08
    Activations Density 0.002%

    No Known Activations