© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1096
    Prev
    Next
    INDEX
    Explanations

    continents and regions

    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
    åħ¨åİ¿
    -0.30
    该åİ¿
    -0.26
    缴æĴŃéĹ´
    -0.26
    vero
    -0.25
    éķĩæĶ¿åºľ
    -0.25
    County
    -0.24
    车åºĵ
    -0.24
    æŃ£å¸¸ä½¿çĶ¨
    -0.23
    åİ¿éķ¿
    -0.23
    åİ¿æĶ¿åºľ
    -0.23
    POSITIVE LOGITS
    åIJĦåĽ½
    0.49
     countries
    0.40
    åħ¶ä»ĸåĽ½å®¶
    0.38
     nations
    0.33
     Countries
    0.31
    countries
    0.31
    åľ°åĮºçļĦ
    0.31
    èĮĥåĽ´åĨħ
    0.30
    region
    0.30
     region
    0.30
    Activations Density 0.067%

    No Known Activations