© 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. 849
    Prev
    Next
    INDEX
    Explanations

    speech attribution after quote

    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
    è¦ģæĬĬ
    -0.24
    able
    -0.24
    <|endoftext|>
    -0.23
    åı¯ä»¥æĬĬ
    -0.23
    ught
    -0.23
    ä¸ĭ
    -0.23
    çĦ¶æĺ¯
    -0.21
     (...)
    -0.21
    è¦ģ
    -0.21
    éĢļåħ³
    -0.21
    POSITIVE LOGITS
    said
    0.50
    她说
    0.46
     said
    0.45
    says
    0.41
    ä»ĸ表示
    0.40
    ä»ĸ说
    0.40
    è¨ĺèĢħ
    0.37
    æį®
    0.37
     dijo
    0.35
    ä¸ļåĨħ人士
    0.35
    Activations Density 0.125%

    No Known Activations