© 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. 22136
    Prev
    Next
    INDEX
    Explanations

    chemical industry, company, and process

    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
    磨æįŁ
    -0.09
    æĥħ人
    -0.09
     Gems
    -0.08
    æľįåĬ¡æľºæŀĦ
    -0.08
    çIJĨåıij
    -0.08
    离åİ»
    -0.08
    æĢķ
    -0.08
     اÙĦÙĥرÙĬÙħ
    -0.08
    åĬ¨æĦŁ
    -0.08
    ä½ľèĢħæīĢæľī
    -0.08
    POSITIVE LOGITS
    è¡Įä¸ļ
    0.11
    åĮĸåѦåĵģ
    0.10
    è¡Įä¸ļä¸Ń
    0.10
    woff
    0.09
    industry
    0.09
     Industry
    0.09
    åİŁæĸĻ
    0.09
    ç§ijæĻ®
    0.08
    éģ¨
    0.08
    管线
    0.08
    Activations Density 0.021%

    No Known Activations