© 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. 13139
    Prev
    Next
    INDEX
    Explanations

    leadership and management roles

    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
    åĩī
    -0.21
    .percent
    -0.20
    ç§ijçłĶéĻ¢
    -0.20
     cooled
    -0.19
    涼
    -0.19
    訾
    -0.19
    vig
    -0.19
    angs
    -0.19
    -publish
    -0.19
    rocket
    -0.18
    POSITIVE LOGITS
    æĮĩæĮ¥
    0.28
    绣é¢Ĩ
    0.26
    å²Ĺä½į
    0.25
    -level
    0.25
    æīĭä¸ĭ
    0.25
    级åĪ«çļĦ
    0.23
    å±Ĥ次
    0.23
    çĿ£
    0.22
    级åĪ«
    0.22
    -Level
    0.22
    Activations Density 0.053%

    No Known Activations