© 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. 11398
    Prev
    Next
    INDEX
    Explanations

    situations, roles, or life stages

    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
    樱èĬ±
    -0.20
    æĻ°
    -0.19
    yers
    -0.19
    vic
    -0.19
    éĺĶ
    -0.19
    çı¥
    -0.19
    çĵ¶é¢Ī
    -0.18
    é£ı
    -0.18
    DATES
    -0.18
    æĤĶ
    -0.18
    POSITIVE LOGITS
     formal
    0.22
    æ¡ģ
    0.21
     complement
    0.21
    åħ¼èģĮ
    0.21
    æĶ¾æĿ¾
    0.20
    inox
    0.20
    æŃ£å¼ı
    0.20
    ä¸ĭçıŃ
    0.20
     Formal
    0.19
    åĶ±æŃĮ
    0.19
    Activations Density 0.265%

    No Known Activations