© 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. 10704
    Prev
    Next
    INDEX
    Explanations

    scoring position or home run

    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
    é«ĺä½İ
    -0.21
     suppress
    -0.20
    åĿij
    -0.20
    hq
    -0.20
    ä¸ĸ家
    -0.20
    æĮº
    -0.20
    ä»ĭåħ¥
    -0.19
    ington
    -0.19
     dev
    -0.19
    æĿŀ
    -0.19
    POSITIVE LOGITS
    abee
    0.21
    slides
    0.20
    gesture
    0.20
    PEAR
    0.19
    erox
    0.18
    åĨ²æ´Ĺ
    0.18
    xdb
    0.18
     Transport
    0.17
    Manufacturer
    0.17
    piler
    0.17
    Activations Density 0.001%

    No Known Activations