© 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. 10779
    Prev
    Next
    INDEX
    Explanations

    of interest

    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
    arian
    -0.19
    äºĨä¸Ģ份
    -0.19
    éĤº
    -0.19
    ÑĢаÑī
    -0.18
    into
    -0.17
    ä¸Ģ份
    -0.17
    otta
    -0.17
    otation
    -0.17
    ä»Ģä¹Īæł·
    -0.17
    ús
    -0.16
    POSITIVE LOGITS
    æīĢåľ¨
    0.23
     interest
    0.20
     Interest
    0.20
    æīĢåľ¨çļĦ
    0.18
    Interest
    0.18
    ä¹ĭå¤Ħ
    0.18
    wend
    0.17
    广大
    0.17
    æĦŁåħ´è¶£çļĦ
    0.17
    人士
    0.17
    Activations Density 0.023%

    No Known Activations