© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 965
    Prev
    Next
    INDEX
    Explanations

    customer service representative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    çĤ®
    -0.29
    ubb
    -0.25
     RENDER
    -0.24
    æĢĿç´¢
    -0.24
     inex
    -0.24
    cheap
    -0.23
    redd
    -0.23
    æ²īè¿·
    -0.22
    ä¹ł
    -0.22
    奢ä¾Ī
    -0.22
    POSITIVE LOGITS
     escalate
    0.30
    ä¸Ģéģį
    0.27
     authenticate
    0.26
     escalated
    0.26
    便æ°ij
    0.26
     authenticated
    0.25
    为æĤ¨
    0.25
     authentication
    0.25
    客æľį
    0.24
    око
    0.24
    Activations Density 0.021%

    No Known Activations