© 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. 12091
    Prev
    Next
    INDEX
    Explanations

    stages of competition

    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
    ashington
    -0.18
     Hund
    -0.18
    èľĪ
    -0.17
    ymax
    -0.17
    hey
    -0.17
    åģıåģı
    -0.16
    illis
    -0.16
    oku
    -0.16
    ä¹ĭ乡
    -0.16
    UIL
    -0.16
    POSITIVE LOGITS
    åIJ«
    0.19
    isch
    0.18
    uran
    0.18
    峡
    0.18
    oran
    0.18
    åıĬ以ä¸Ĭ
    0.18
    ische
    0.18
    etro
    0.18
     stash
    0.17
    å¾Ħ
    0.17
    Activations Density 0.004%

    No Known Activations