© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1736
    Prev
    Next
    INDEX
    Explanations

    copyright laws and piracy regulation

    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
    elage
    -0.30
    éļ¾å¿ĺ
    -0.26
    è£ħéħįå¼ı
    -0.26
     elevation
    -0.26
    çıŃéķ¿
    -0.26
     preparation
    -0.25
     Preparation
    -0.25
    診
    -0.25
    weather
    -0.25
     barracks
    -0.25
    POSITIVE LOGITS
     piracy
    0.41
    侵害
    0.38
    èijĹä½ľæĿĥ
    0.36
    é»ij客
    0.35
    ä¾µæĿĥ
    0.35
     Internet
    0.35
    让æ¶Īè´¹èĢħ
    0.34
     enforcement
    0.34
    ç»´æĿĥ
    0.34
    äºĴèģĶç½ij
    0.33
    Activations Density 0.042%

    No Known Activations