© 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. 16772
    Prev
    Next
    INDEX
    Explanations

    experienced coach or veteran team member

    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
    éĻĽ
    -0.22
    æĹłåĬĽ
    -0.22
    æĹłç¼ĺ
    -0.21
    åħ´èµ·
    -0.19
    çĦļ
    -0.19
    æī¼
    -0.19
    éĸĴ
    -0.19
    èĤ¢
    -0.18
    éĿĴæĺ¥
    -0.18
    å¿ĥæĢĿ
    -0.18
    POSITIVE LOGITS
    ç»ıéªĮ
    0.36
    ç»ıéªĮ丰å¯Į
    0.35
    ç»ıéªĮåĴĮ
    0.34
     experience
    0.32
    éĺħåİĨ
    0.30
    çļĦç»ıéªĮ
    0.29
    ç¶ĵé©Ĺ
    0.29
    æĪIJçĨŁ
    0.28
     experienced
    0.27
     Experience
    0.27
    Activations Density 0.015%

    No Known Activations