© 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. 11384
    Prev
    Next
    INDEX
    Explanations

    distance and location

    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
    orny
    -0.21
    ä¸ĢæŶ
    -0.20
    erosis
    -0.19
     lump
    -0.19
    æļ¾
    -0.19
    è¯ŀ
    -0.19
    нал
    -0.18
    顽
    -0.18
     catalog
    -0.18
    omy
    -0.18
    POSITIVE LOGITS
    便åĪ©
    0.25
    æ³
    0.23
     literally
    0.23
    åı¯ä»¥çĽ´æİ¥
    0.22
    身å¤Ħ
    0.21
    家éŨåı£
    0.21
    urally
    0.21
    å°ģ
    0.20
    å¾Īæĸ¹ä¾¿
    0.19
    æīĢåľ¨çļĦ
    0.19
    Activations Density 0.035%

    No Known Activations