© 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. 2014
    Prev
    Next
    INDEX
    Explanations

    protection against

    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
    èĥ½æ»¡è¶³
    -0.25
     dedic
    -0.24
     stark
    -0.23
    æĭ¼åij½
    -0.22
     devoted
    -0.22
    -space
    -0.21
     емÑĥ
    -0.21
    çļĦç¡®
    -0.21
    ä¸įä¹ħ
    -0.21
    åħħè£ķ
    -0.20
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.30
    åIJĦç§į
    0.30
    lder
    0.27
    æĿ¥èĩªäºİ
    0.25
    ลม
    0.25
    å¤ĸæĿ¥
    0.24
    ä¸ĩä¸Ģ
    0.24
     overposting
    0.24
    æŶéĹ´åĴĮ
    0.23
    å¤ĸçķĮ
    0.23
    Activations Density 0.048%

    No Known Activations