© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 401
    Prev
    Next
    INDEX
    Explanations

    governor names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    ç²¾çĽĬæ±Ĥç²¾
    -0.26
    æĬ¤èº«
    -0.25
    è¿Ľä¿®
    -0.25
    æĢĿç»´æĸ¹å¼ı
    -0.25
    鲨
    -0.25
    æ²¹çĶ°
    -0.24
    è¿Ļç§įæĸ¹æ³ķ
    -0.24
    åħ¨å¥Ĺ
    -0.24
    olv
    -0.23
    usal
    -0.23
    POSITIVE LOGITS
     administration
    0.34
     Administration
    0.34
     statewide
    0.32
     Governor
    0.31
    æī§æĶ¿
    0.31
     bipartisan
    0.30
     governor
    0.29
     governing
    0.29
     Administr
    0.28
    åİ¿éķ¿
    0.28
    Activations Density 0.059%

    No Known Activations