© 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. 1069
    Prev
    Next
    INDEX
    Explanations

    date, location, or topic

    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
     additionally
    -0.29
     moreover
    -0.27
     however
    -0.25
    _TC
    -0.23
     likewise
    -0.23
    however
    -0.23
     depended
    -0.22
    zew
    -0.22
    GMEM
    -0.22
     therefore
    -0.22
    POSITIVE LOGITS
    åıijå¸ĥæŶéĹ´
    0.31
    ä½ľèĢħ
    0.29
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.26
    Ùĥاتب
    0.24
    æĸĩç«łæĿ¥æºIJ
    0.24
    æĿ¥æºIJ
    0.24
    ä¸ĵé¢ĺ
    0.23
     Dear
    0.23
    åŁºæľ¬ä¿¡æģ¯
    0.23
    ðŁĶį
    0.23
    Activations Density 1.413%

    No Known Activations