© 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. 38790
    Prev
    Next
    INDEX
    Explanations

    accidents and injuries

    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
    缯
    -0.11
    请èģĶç³»
    -0.11
    æĸ°åŀĭåĨłçĬ¶
    -0.10
    çIJĨä¼ļ
    -0.09
    ä¸įå½±åĵį
    -0.09
    éĹ®éĹ®
    -0.09
    ç½ijå°ıç¼ĸ
    -0.09
    åĭŁéĽĨ
    -0.09
    æľīæ¯Ĵ
    -0.09
    ä¸Ģèĩ´æĢ§
    -0.09
    POSITIVE LOGITS
    nit
    0.08
    家éķ¿
    0.08
    头éĥ¨
    0.08
    hek
    0.08
    خار
    0.08
    PYTHON
    0.08
    åĪĽ
    0.08
    æµĴ
    0.07
     baseUrl
    0.07
    aru
    0.07
    Activations Density 0.155%

    No Known Activations