© 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. 593
    Prev
    Next
    INDEX
    Explanations

    examination of

    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
    éĤ£æł·çļĦ
    -0.24
    Pts
    -0.24
    HERE
    -0.23
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.23
    è¿Ļæł·
    -0.23
    —which
    -0.23
    uity
    -0.23
    èĢĮåľ¨
    -0.23
    å°Ĩåħ¶
    -0.22
     inev
    -0.22
    POSITIVE LOGITS
    缮çļĦæĺ¯
    0.27
    éĽĨåIJĪ
    0.25
    缮çļĦåľ¨äºİ
    0.23
    缼ä¼ļ
    0.22
     Useful
    0.21
    owi
    0.21
    çķĮ第ä¸Ģ
    0.21
    å¥
    0.21
     accessible
    0.21
    quisition
    0.21
    Activations Density 0.235%

    No Known Activations