© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14767
    Prev
    Next
    INDEX
    Explanations

    LICENSE BLOCK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    nish
    -0.19
    èĴ¿
    -0.19
    鸥
    -0.19
    衲
    -0.19
    ourage
    -0.19
    éĤ£ä½į
    -0.19
     Transitional
    -0.19
     Cups
    -0.18
    èİĵ
    -0.18
    åij¨åĪĬ
    -0.18
    POSITIVE LOGITS
    大å®ĹåķĨåĵģ
    0.20
    è´¸
    0.19
    åĨ²çªģ
    0.19
    æIJª
    0.19
    çĪª
    0.19
    å·©åĽº
    0.19
    诸侯
    0.18
    触
    0.18
    è¡ĮåĪĹ
    0.18
    æĥľ
    0.18
    Activations Density 0.007%

    No Known Activations