© 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. 18141
    Prev
    Next
    INDEX
    Explanations

    business and IT communication

    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
    /Gate
    -0.09
    ç´į
    -0.09
    鬲
    -0.09
    殿
    -0.09
    Chip
    -0.09
    æĪİ
    -0.09
    æĸĩåĪĽ
    -0.09
    (feed
    -0.09
     censor
    -0.09
    åĩ»
    -0.09
    POSITIVE LOGITS
    åĬŀåħ¬
    0.11
    ä¸Ģéĥ¨
    0.10
    交éĻħ
    0.09
     office
    0.08
     IT
    0.08
    _SUITE
    0.08
    wf
    0.08
    à¸Ĥà¸Ļ
    0.08
    -office
    0.08
    ansa
    0.08
    Activations Density 0.182%

    No Known Activations