© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    equal comparison or ranking

    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
    æľīçĶ¨çļĦ
    -0.24
    ertime
    -0.23
    ä¸įæĸŃçļĦ
    -0.23
    æľīçĶ¨
    -0.22
    åĭŁ
    -0.22
     mater
    -0.22
    è°ĥ
    -0.22
    çļĦä¸ĢåĪĩ
    -0.22
    _RW
    -0.21
    磾
    -0.21
    POSITIVE LOGITS
    æĮģå¹³
    0.36
     identical
    0.34
     multiple
    0.32
     equally
    0.29
     equal
    0.29
    åıĮåıĮ
    0.28
     equality
    0.27
    å¤ļåľ°
    0.27
     simultaneously
    0.27
     concurrently
    0.27
    Activations Density 0.096%

    No Known Activations