© 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. 15968
    Prev
    Next
    INDEX
    Explanations

    scored points and led wins

    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
    åĢĻ
    -0.22
    æ¸´æľĽ
    -0.22
    aming
    -0.20
    å®ģæĦ¿
    -0.19
    èĢĮçİ°åľ¨
    -0.19
    licence
    -0.18
     prefect
    -0.18
     part
    -0.18
    åĪ°çİ°åľ¨
    -0.18
    è°ģèĥ½
    -0.18
    POSITIVE LOGITS
    ql
    0.18
    å¸ĤæķĻèĤ²
    0.18
    ç½ijé¦ĸ页
    0.18
    è·Įå¹ħ
    0.18
    kos
    0.17
    èĭ¹
    0.17
    ä¸Ģ对ä¸Ģ
    0.17
    wat
    0.17
    åįķåĵģ
    0.17
    wc
    0.17
    Activations Density 0.006%

    No Known Activations