© 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. 13682
    Prev
    Next
    INDEX
    Explanations

    DRAM and RAM memory

    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
     uLocal
    -0.24
     sourceMapping
    -0.23
    auté
    -0.22
    essler
    -0.21
    ucker
    -0.21
    orca
    -0.21
    alla
    -0.21
    íĪ´
    -0.21
    ASA
    -0.21
    楦
    -0.20
    POSITIVE LOGITS
    åİĤåķĨ
    0.26
    ä¾ĽåºĶåķĨ
    0.24
    æĿ¡
    0.24
    æĶ¿åºľéĩĩè´Ń
    0.22
     vendor
    0.21
     sidel
    0.21
     memory
    0.21
    åĨħåŃĺ
    0.21
    å·¥ä¸ļ大åѦ
    0.20
    绣ä¸Ģ
    0.20
    Activations Density 0.028%

    No Known Activations