© 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. 53
    Prev
    Next
    INDEX
    Explanations

    Microsoft, Mozilla, Nintendo, Apache software

    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
    ToObject
    -0.23
    èĬĹ
    -0.23
    .binding
    -0.22
    å©Ĭ
    -0.22
    _residual
    -0.21
    æľĪåĪĿ
    -0.21
     salopes
    -0.21
    çѦ
    -0.21
     seriousness
    -0.21
     negativity
    -0.21
    POSITIVE LOGITS
    åı«åģļ
    0.31
     called
    0.29
     Ras
    0.28
    åı«
    0.28
    称为
    0.26
     '
    0.25
     SL
    0.24
    åIJįåı«
    0.24
    ument
    0.24
     popular
    0.24
    Activations Density 0.167%

    No Known Activations