© 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. 378
    Prev
    Next
    INDEX
    Explanations

    road bicycle cycling races

    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
    åħ¬å®īå±Ģ
    -0.26
    对åŃ©åŃIJ
    -0.25
     grandchildren
    -0.25
     Matrix
    -0.25
    çļĦåŃ©åŃIJ
    -0.25
    让åŃ©åŃIJ
    -0.24
    ç¬ijèĦ¸
    -0.24
    ç»ĻåŃ©åŃIJ
    -0.23
    åħīçĶµ
    -0.23
     MATRIX
    -0.23
    POSITIVE LOGITS
     cyclist
    0.51
     cyclists
    0.49
    éªijè¡Į
    0.49
    èĩªè¡Į车
    0.44
     Cycling
    0.42
     bike
    0.41
     bicycle
    0.41
     bikes
    0.40
     Bicycle
    0.37
     bicycles
    0.37
    Activations Density 0.061%

    No Known Activations