© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11446
    Prev
    Next
    INDEX
    Explanations

    rugby, cup, championship, madness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ä¸Ģæīĭ
    -0.23
    é¦Ĩ
    -0.20
    enge
    -0.20
    éĻ¢
    -0.20
    æĿĸ
    -0.19
     whom
    -0.19
    åĢij
    -0.18
    å´½
    -0.18
    -eye
    -0.18
    館
    -0.18
    POSITIVE LOGITS
    åIJĦåĽ½
    0.21
    ä½ĵç³»
    0.20
    åĮºåŁŁåĨħ
    0.19
    odial
    0.19
    çľģ份
    0.19
    诸侯
    0.19
    åī©ä¸ĭ
    0.18
    è¯Ħæ¯Ķ
    0.18
    jour
    0.18
    çĶ¥
    0.18
    Activations Density 0.006%

    No Known Activations