© 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. 1153
    Prev
    Next
    INDEX
    Explanations

    arthurian knights and legends

    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
    æĻ®æŁ¥
    -0.24
    èIJİ缩
    -0.23
    çīĸ
    -0.23
    æł¸ç®Ĺ
    -0.23
    çĩ¥
    -0.23
    /tiny
    -0.22
    åı£è¢ĭ
    -0.22
    åį°å°¼
    -0.22
    æĻļ
    -0.22
    åĪĴ
    -0.22
    POSITIVE LOGITS
     knight
    0.50
     knights
    0.49
    éªij士
    0.43
     Knight
    0.37
     princess
    0.34
     Knights
    0.31
     medieval
    0.31
     Rider
    0.30
    é¨İ
    0.30
    Knight
    0.29
    Activations Density 0.023%

    No Known Activations