© 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. 16590
    Prev
    Next
    INDEX
    Explanations

    office, GM, director, principal

    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
    Personal
    -0.21
    personal
    -0.19
    _easy
    -0.19
    loop
    -0.19
    .drawer
    -0.19
    é£İè²Į
    -0.18
    classname
    -0.18
    个人
    -0.18
     Personal
    -0.18
    NotFoundException
    -0.18
    POSITIVE LOGITS
    /engine
    0.21
     talent
    0.21
    åĴĮæĬĢæľ¯
    0.21
    é²ij
    0.19
     Talent
    0.19
    åħ¼
    0.19
    .acquire
    0.19
     Salv
    0.19
    çŃĸçķ¥
    0.19
    ateur
    0.18
    Activations Density 0.013%

    No Known Activations