© 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. 16702
    Prev
    Next
    INDEX
    Explanations

    law enforcement and investigations

    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
     term
    -0.21
     min
    -0.20
     start
    -0.20
    ç³Ĭ
    -0.20
    ç³ł
    -0.19
    æĢĻ
    -0.19
    æıĸ
    -0.19
     moder
    -0.19
     dictator
    -0.19
     quake
    -0.18
    POSITIVE LOGITS
    åıĭè°Ĭ
    0.23
    æŃ£ä¹ī
    0.23
    èģĶåIJĪ
    0.22
    åĬ©çIJĨ
    0.22
    åįıä½ľ
    0.21
    ä¾¦æŁ¥
    0.21
    å·¥ä½ľäººåijĺ
    0.20
    åĽ½éĻħåIJĪä½ľ
    0.20
    åIJĪåĬĽ
    0.20
    åıĭæĥħ
    0.20
    Activations Density 0.019%

    No Known Activations