© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52742
    Prev
    Next
    INDEX
    Explanations

    remediation of contaminated sites

    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
    åı¸é©¬
    -0.10
    åĨ²åĬ¨
    -0.09
    å£ģ
    -0.09
    å£ĵåĬĽ
    -0.09
     scarc
    -0.09
     ØŃص
    -0.09
    æķ¬ä¸ļ
    -0.08
    íħľ
    -0.08
    åİĭåĬĽ
    -0.08
    åĴ½åĸī
    -0.08
    POSITIVE LOGITS
     remed
    0.13
    æķ´æ²»
    0.11
     Sites
    0.11
     Remed
    0.11
    site
    0.11
    æ²»çIJĨ
    0.10
    æľīæ¯Ĵ
    0.10
    Site
    0.10
     Site
    0.10
     sites
    0.09
    Activations Density 0.124%

    No Known Activations