© 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. 11789
    Prev
    Next
    INDEX
    Explanations

    record deal

    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
     vá»įng
    -0.20
    设æĥ³
    -0.20
    ãĥŀãĥ«
    -0.20
    éľİ
    -0.20
    Suffix
    -0.19
    鸽
    -0.19
    æĪij们åı¯ä»¥
    -0.19
    ä¸Ģçķª
    -0.18
    odian
    -0.18
    æĮĽ
    -0.18
    POSITIVE LOGITS
    çľŁç©º
    0.23
     Vacuum
    0.23
    åĬ¨æijĩ
    0.21
    è¾ĵç»Ļ
    0.20
    pé
    0.19
     vacuum
    0.19
    [Index
    0.19
     Vac
    0.19
     embarrass
    0.19
    丢失
    0.19
    Activations Density 0.113%

    No Known Activations