© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 80
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
    feed
    -0.23
    éĴ¿
    -0.23
     onItemClick
    -0.23
     Propel
    -0.22
     bolts
    -0.22
    oppers
    -0.22
    æľĿ
    -0.22
    建档ç«ĭåį¡
    -0.22
    å¹³åĿĩ
    -0.22
    满
    -0.22
    POSITIVE LOGITS
     edit
    0.28
     vandal
    0.28
    suggest
    0.27
     Cleanup
    0.26
    /request
    0.26
    è¿·æĥij
    0.25
     Edit
    0.25
    /rfc
    0.25
    ä¿®æĶ¹
    0.24
    .REQUEST
    0.24
    Activations Density 0.008%

    No Known Activations