© 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. 45
    Prev
    Next
    INDEX
    Explanations

    main character

    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
    emode
    -0.26
     NXT
    -0.24
    ulla
    -0.24
    edImage
    -0.24
    ÑĮÑİ
    -0.24
    ableView
    -0.23
     BTN
    -0.23
    æĪ¿
    -0.22
    owania
    -0.22
    ä¼ļè®®
    -0.22
    POSITIVE LOGITS
     protagonist
    0.40
    主è§Ĵ
    0.39
    主人åħ¬
    0.34
    人çī©
    0.34
     protagonists
    0.32
    .hero
    0.31
     hero
    0.31
    -hero
    0.30
    女主è§Ĵ
    0.28
    characters
    0.27
    Activations Density 0.023%

    No Known Activations