© 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. 12748
    Prev
    Next
    INDEX
    Explanations

    packet handling or encryption

    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
    ral
    -0.23
    ä¸Ģåı°
    -0.22
    abus
    -0.21
    æŃĮèĪŀ
    -0.20
    åħ»
    -0.19
    lag
    -0.19
    çįł
    -0.19
    æĭĸæ¬ł
    -0.18
    æŀ¶åŃIJ
    -0.18
     Hawkins
    -0.18
    POSITIVE LOGITS
    .asc
    0.20
    (sigma
    0.19
    :pk
    0.19
     torture
    0.18
    çĸ¼çĹĽ
    0.18
     pem
    0.18
    .Parcelable
    0.18
    èĪªè¿IJ
    0.18
    å·¥ä½ľç«Ļ
    0.17
     embar
    0.17
    Activations Density 0.037%

    No Known Activations