© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14979
    Prev
    Next
    INDEX
    Explanations

    cough, cold, eyes, sickness

    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
    æ£į
    -0.22
    è°Ĩ
    -0.20
    红线
    -0.20
    erial
    -0.20
    actable
    -0.18
     Lit
    -0.18
    CommandLine
    -0.18
    éĵ¢
    -0.18
    åĮĸçļĦ
    -0.18
    é«ĺ强度
    -0.18
    POSITIVE LOGITS
    äºĨä¸Ģä¸ĭ
    0.26
    ä¸Ģä¸ĭ
    0.23
    è¿ĩåIJİ
    0.21
    ä¸Ģ声
    0.20
    _rl
    0.20
    å¹ħ度
    0.20
    Ùħض
    0.19
    Globals
    0.19
    shaw
    0.19
     gust
    0.19
    Activations Density 0.012%

    No Known Activations