© 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. 1454
    Prev
    Next
    INDEX
    Explanations

    electronic devices and software

    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
    ired
    -0.08
    åĮı
    -0.08
    uum
    -0.07
    èģĬ天
    -0.07
    çļĦä¸Ģ
    -0.07
    ç«Ł
    -0.07
     practice
    -0.07
    omat
    -0.07
    æµij
    -0.07
     using
    -0.07
    POSITIVE LOGITS
    è¶³å¤Ł
    0.15
    è¶³å¤ŁçļĦ
    0.12
    åı¯ä¾Ľ
    0.12
    æĬĬè¿ĻäºĽ
    0.11
    è¿Ļè¯Ŀ
    0.10
    çĻ½éĽª
    0.10
    çļĦåīįæıIJä¸ĭ
    0.10
    åľŁè±ª
    0.09
     Anita
    0.09
    adora
    0.09
    Activations Density 0.156%

    No Known Activations