© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2270
    Prev
    Next
    INDEX
    Explanations

    data transmission speed

    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
    èµĦäº§è´ŁåĢº
    -0.29
     sustainability
    -0.25
     Sustainability
    -0.24
     sprink
    -0.23
     Pills
    -0.23
    管çIJĨå±Ĥ
    -0.23
    heits
    -0.23
    æ¶ħ
    -0.22
    åľ¨åħ¨åĽ½
    -0.22
     Garrison
    -0.22
    POSITIVE LOGITS
     maximum
    0.36
    éĢŁåº¦
    0.36
     speed
    0.35
     speeds
    0.34
    çļĦæľĢ大
    0.33
    Maximum
    0.33
     transfer
    0.33
     throughput
    0.33
    .getMax
    0.32
     getMax
    0.32
    Activations Density 0.044%

    No Known Activations