© 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. 15418
    Prev
    Next
    INDEX
    Explanations

    actors and names

    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
    è¹Ī
    -0.22
    è£ģå®ļ
    -0.22
    éŃĶ鬼
    -0.20
    é¢ĦåijĬ
    -0.20
    èĭĮ
    -0.20
    究
    -0.19
    æĪ¾
    -0.19
    éĻĮ
    -0.19
    .invoke
    -0.18
    红线
    -0.18
    POSITIVE LOGITS
    æĹ¥æ¶Īæģ¯
    0.19
     Hutch
    0.18
    Outlet
    0.18
    å¸ľ
    0.18
    iefs
    0.17
    _weather
    0.17
    çĦĻ
    0.17
     whiskey
    0.17
     fragile
    0.17
    çħ¦
    0.17
    Activations Density 0.014%

    No Known Activations