© 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. 11283
    Prev
    Next
    INDEX
    Explanations

    official, referee, umpire, judge, jury

    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
     hero
    -0.23
    æŃĮ
    -0.21
    çıŃ车
    -0.20
    èĭ±éĽĦ
    -0.19
    è°ģéĥ½
    -0.19
    åIJĪçIJĨçļĦ
    -0.19
    ä¸įåģľçļĦ
    -0.19
     heroine
    -0.19
    Scan
    -0.18
    actal
    -0.18
    POSITIVE LOGITS
    è£ģåĪ¤
    0.28
    åħ¬æŃ£
    0.27
    仲è£ģ
    0.26
    æī§æ³ķ
    0.25
    åijĺ
    0.23
    è§Ĵèī²
    0.22
    çĽijçĿ£
    0.22
    åħ¨ç¨ĭ
    0.21
    èģĮè´£
    0.21
    èµĦæł¼
    0.20
    Activations Density 0.043%

    No Known Activations