© 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. 2111
    Prev
    Next
    INDEX
    Explanations

    library, lib, libraries

    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´é£İ
    -0.26
    第ä¸ĢæĿ¡
    -0.24
    ViewModel
    -0.24
    StandardItem
    -0.24
    MainFrame
    -0.24
    以人为
    -0.23
    osas
    -0.23
    upe
    -0.22
    (typ
    -0.22
     phased
    -0.22
    POSITIVE LOGITS
    åºĵ
    0.37
     library
    0.36
     libr
    0.32
     libraries
    0.28
     optionally
    0.28
     LIB
    0.28
    lib
    0.28
    åĽ¾ä¹¦é¦Ĩ
    0.27
     version
    0.26
    Lib
    0.26
    Activations Density 0.387%

    No Known Activations