© 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. 12143
    Prev
    Next
    INDEX
    Explanations

    setting focus or emphasis

    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
    çĤ¬
    -0.19
    Rol
    -0.18
    è¿ĩåħ³
    -0.18
    è§ģè¯ģ
    -0.18
    Stand
    -0.18
     butcher
    -0.18
    è°ģçŁ¥éģĵ
    -0.17
    ungs
    -0.17
    ä»»ä½ķ人
    -0.17
    误ä¼ļ
    -0.17
    POSITIVE LOGITS
     focus
    0.49
     focuses
    0.41
    focus
    0.40
    åħ³æ³¨
    0.37
    Focus
    0.37
     focused
    0.36
    çļĦéĩįçĤ¹
    0.35
    çĦ¦çĤ¹
    0.35
     Focus
    0.34
    .focus
    0.34
    Activations Density 0.099%

    No Known Activations