© 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. 30903
    Prev
    Next
    INDEX
    Explanations

    natural gas industry

    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
    åĴĮæĬĢæľ¯
    -0.09
    åľĪ
    -0.09
    Sites
    -0.09
    æ¡£
    -0.09
    追
    -0.09
    èĬĿ麻
    -0.09
    è¾Ī
    -0.09
    oppins
    -0.08
     Kann
    -0.08
    .getCount
    -0.08
    POSITIVE LOGITS
    ä¸įåħĭ
    0.10
    ç»Ļèĩªå·±
    0.09
    åŁŃ
    0.09
    æĬĬ她
    0.09
    æĺ¯ä¸įåı¯èĥ½
    0.09
     misc
    0.09
    æĿĤ
    0.08
    berger
    0.08
    åıĪ好
    0.08
    大æ¦Ĥæĺ¯
    0.08
    Activations Density 0.050%

    No Known Activations