© 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. 13768
    Prev
    Next
    INDEX
    Explanations

    meal or breakfast time

    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
    èī¯å¿ĥ
    -0.19
    çīĩåŃIJ
    -0.19
    agens
    -0.19
     bikini
    -0.18
    haft
    -0.18
    porno
    -0.18
    _$_
    -0.17
    çĪ¿
    -0.17
     tatto
    -0.17
    otten
    -0.17
    POSITIVE LOGITS
    é¤IJ
    0.27
     meal
    0.25
    çĶ¨é¤IJ
    0.24
    æ¡Įä¸Ĭ
    0.23
     meals
    0.23
    æĹ©é¤IJ
    0.22
    ä»İ容
    0.21
    æĻļé¤IJ
    0.20
    æĻļé¥Ń
    0.20
    time
    0.20
    Activations Density 0.032%

    No Known Activations