© 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. 565
    Prev
    Next
    INDEX
    Explanations

    law / duty / tradition

    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
    -target
    -0.34
    Target
    -0.32
     NASA
    -0.30
    targets
    -0.30
    æ¯ĶæĪij
    -0.29
     Target
    -0.28
    NASA
    -0.28
    ำ
    -0.27
     targeting
    -0.26
     Targets
    -0.25
    POSITIVE LOGITS
     tradition
    0.42
     traditionally
    0.40
    ä¼łç»Ł
    0.39
     juris
    0.39
     doctrine
    0.39
     traditions
    0.37
     doctrines
    0.37
     principles
    0.37
    ä¼łç»ŁçļĦ
    0.35
     traditional
    0.34
    Activations Density 0.051%

    No Known Activations