© 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. 16353
    Prev
    Next
    INDEX
    Explanations

    civil servant bureaucracy paperwork cadre

    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
    æīª
    -0.22
    ÑĢÑĥÑĪ
    -0.19
    rael
    -0.18
    æ¼¾
    -0.18
    utra
    -0.17
    OrCreate
    -0.17
    åıijå±ķæľºéģĩ
    -0.17
    被çĽĹ
    -0.17
    å¾ģæ±Ĥ
    -0.17
    ëĿ¼ë©´
    -0.17
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.21
    /pol
    0.19
    istical
    0.19
    istration
    0.19
    æľºæŀĦ
    0.19
    /Admin
    0.19
    åĮĸçļĦ
    0.19
    åĥļ
    0.19
     nightmare
    0.18
    icc
    0.17
    Activations Density 0.010%

    No Known Activations