© 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. 14068
    Prev
    Next
    INDEX
    Explanations

    wrapping, packaging

    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
     sensible
    -0.19
    åıĸè¯ģ
    -0.19
    éħ¿éħĴ
    -0.19
    åĥįãģı
    -0.19
    èIJ½æĪ·
    -0.18
    Ale
    -0.18
    ä¿ļ
    -0.18
     launder
    -0.18
    eras
    -0.18
    æĥĭ
    -0.18
    POSITIVE LOGITS
    fault
    0.20
    orthy
    0.20
    è¿ĩçļĦ
    0.20
    åĮ¹
    0.20
    å¯Ĥå¯ŀ
    0.19
     gift
    0.19
    æķ¦
    0.19
    ä¹ĭæĺŁ
    0.19
    FAULT
    0.19
    eki
    0.19
    Activations Density 0.004%

    No Known Activations