© 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. 30100
    Prev
    Next
    INDEX
    Explanations

    protecting and preserving the environment

    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
    主æĿĥ
    -0.10
    å®īæĬļ
    -0.09
    borg
    -0.09
    bour
    -0.09
    ä»ĭåħ¥
    -0.09
    大ä¼ļ
    -0.08
     Perry
    -0.08
    åij½é¢ĺ
    -0.08
    æķijæĬ¤
    -0.08
     Pais
    -0.08
    POSITIVE LOGITS
    çİ°æľīçļĦ
    0.09
    伸
    0.09
    Buzz
    0.09
    åİŁæľīçļĦ
    0.09
    身边çļĦ
    0.09
    omat
    0.09
    arer
    0.09
    åĴĮåıijå±ķ
    0.09
    éĢ¶
    0.08
    çİ°æľī
    0.08
    Activations Density 0.031%

    No Known Activations