© 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. 14480
    Prev
    Next
    INDEX
    Explanations

    manufacturing, sourcing, labor, farming

    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
    åĿŃ
    -0.24
     Soph
    -0.21
    SupportedContent
    -0.20
     FIRE
    -0.20
    -Mail
    -0.19
    åĩłåĪĨ
    -0.19
     Charts
    -0.19
    纱
    -0.19
     soph
    -0.18
    æĪIJå°±æĦŁ
    -0.18
    POSITIVE LOGITS
    çĶŁäº§
    0.21
    quan
    0.21
    æīĢæīĢ
    0.20
    ä¿¡æģ¯åħ¬å¼Ģ
    0.20
     vag
    0.20
    éĩĩéĽĨ
    0.19
    -specific
    0.19
     bom
    0.19
    oes
    0.19
    äº§åľ°
    0.19
    Activations Density 0.016%

    No Known Activations