© 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. 35226
    Prev
    Next
    INDEX
    Explanations

    pcap capture or network traffic

    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
    溥
    -0.10
    å´©
    -0.09
    ewan
    -0.09
    Emb
    -0.09
     Emb
    -0.09
     systematic
    -0.09
    ãģĦãģŁãģł
    -0.09
    èĢĨ
    -0.08
     rigor
    -0.08
    æĪĺæĸĹåĬĽ
    -0.08
    POSITIVE LOGITS
    æµģéĩı
    0.11
    åıĸè¯ģ
    0.09
    çĵ¶åŃIJ
    0.09
    çļĦ身影
    0.09
    æıŃ
    0.09
    éĻĩ
    0.09
    ç¼ī
    0.09
    干线
    0.09
    æ°ĸ
    0.09
     traffic
    0.09
    Activations Density 0.132%

    No Known Activations