© 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. 12187
    Prev
    Next
    INDEX
    Explanations

    oats or porridge breakfast

    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
    éħ©
    -0.19
    媳
    -0.18
    /her
    -0.17
    æĪ®
    -0.17
    éķ¶åµĮ
    -0.17
    nnen
    -0.17
    åĨľåī¯äº§åĵģ
    -0.17
    .interpolate
    -0.17
    ettings
    -0.17
    orners
    -0.17
    POSITIVE LOGITS
    isma
    0.21
    worm
    0.20
    çĬ¶
    0.18
    æł·çļĦ
    0.18
     stir
    0.18
     cô
    0.17
    loor
    0.17
    ги
    0.17
    bose
    0.17
    æĬ±
    0.17
    Activations Density 0.001%

    No Known Activations