© 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. 21312
    Prev
    Next
    INDEX
    Explanations

    such as

    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
    éĤ£ç§į
    -0.09
    æ·¼
    -0.09
     mãi
    -0.09
    é»ĺé»ĺåľ°
    -0.09
    èIJ¥
    -0.09
    èľľèľĤ
    -0.09
    éĹ¼
    -0.09
     rub
    -0.08
    eni
    -0.08
    æŁIJäºĽ
    -0.08
    POSITIVE LOGITS
    éĩįå·¥
    0.10
    anza
    0.09
    ored
    0.09
    å¼Ģå¿ĥ
    0.09
    åŁºç¡Ģ设æĸ½
    0.09
    lean
    0.09
     dụng
    0.09
    åģļ梦
    0.08
    ä¼łè¨Ģ
    0.08
    ç¼
    0.08
    Activations Density 0.306%

    No Known Activations