© 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. 2989
    Prev
    Next
    INDEX
    Explanations

    compared or differs

    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
    éļIJå½¢
    -0.24
    åĨį度
    -0.23
    assist
    -0.22
    umb
    -0.22
    åIJĪçIJĨçļĦ
    -0.22
    æĸŃ
    -0.22
    éĢĨ转
    -0.22
    便æĺ¯
    -0.22
    åijĬçŁ¥
    -0.21
    sea
    -0.21
    POSITIVE LOGITS
    缸åIJĮ
    0.35
     Compared
    0.35
     compared
    0.35
    åIJĮæł·çļĦ
    0.34
    缸æ¯Ķ
    0.34
    .same
    0.33
     comparatively
    0.33
    åīįèĢħ
    0.33
     differs
    0.33
    缸è¾ĥ
    0.33
    Activations Density 0.718%

    No Known Activations