© 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. 16433
    Prev
    Next
    INDEX
    Explanations

    administrative and support 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
    梯
    -0.21
    ä½ĵéªĮ
    -0.19
    Guid
    -0.18
    éĻ¢éĻ¢å£«
    -0.18
    å¸ĪèµĦ
    -0.18
     subs
    -0.18
    é»ijæļĹ
    -0.18
    éĻ¢åī¯éĻ¢éķ¿
    -0.18
    æī§æķĻ
    -0.18
    sensor
    -0.17
    POSITIVE LOGITS
    åĬŀåħ¬
    0.29
    è¡ĮæĶ¿
    0.25
    ç°¿
    0.24
    administr
    0.23
    å·¥ä½ľ
    0.23
     cler
    0.23
     administrative
    0.22
    礼仪
    0.22
    ç§ĺ书
    0.21
    äºĭå®ľ
    0.21
    Activations Density 0.045%

    No Known Activations