© 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. 345
    Prev
    Next
    INDEX
    Explanations

    killing fields, missing, crimes, massacre, atrocities, during

    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
     rebate
    -0.34
     tester
    -0.28
     hazard
    -0.26
     Emirates
    -0.26
    æĦŁåĨĴ
    -0.24
     lookahead
    -0.24
     mileage
    -0.24
     tweeting
    -0.24
     preview
    -0.24
     forecast
    -0.24
    POSITIVE LOGITS
     systematically
    0.35
    å±łæĿĢ
    0.34
     crimes
    0.34
    åĨ¤
    0.33
    è¡Ģèħ¥
    0.33
    during
    0.32
     atrocities
    0.32
     massacre
    0.32
    During
    0.32
    强奸
    0.31
    Activations Density 0.032%

    No Known Activations