© 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. 13394
    Prev
    Next
    INDEX
    Explanations

    notable people or examples

    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
    ä¸Ģå°ģ
    -0.19
    æĹ¢è¦ģ
    -0.18
     możli
    -0.18
    heimer
    -0.18
    座è°Ī
    -0.17
    æµģåĬ¨
    -0.17
    quiry
    -0.16
    æĹ¶ä»£çļĦ
    -0.16
    eled
    -0.16
    rames
    -0.16
    POSITIVE LOGITS
    ä¹ĭå¤Ħ
    0.32
    mente
    0.26
    ity
    0.21
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.21
    ness
    0.20
    remark
    0.19
    ly
    0.19
    éĿŀåĩ¡
    0.19
    ä¹ĭ举
    0.19
    FEATURE
    0.19
    Activations Density 0.029%

    No Known Activations