© 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. 16569
    Prev
    Next
    INDEX
    Explanations

    comment markers or separators

    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
    åıĺè¿ģ
    -0.20
    .timedelta
    -0.19
     counsel
    -0.18
     Reform
    -0.18
    大大å°ı
    -0.18
    ableView
    -0.17
     Crack
    -0.17
    èĮĹ
    -0.17
    æĸ°åĬł
    -0.17
    chedules
    -0.16
    POSITIVE LOGITS
    屯
    0.21
    ç¯Ļ
    0.20
    ä¸Ģä½ĵ
    0.20
    åŃ¦æľŁ
    0.20
    缯
    0.20
    holm
    0.19
    ä½ľä¸ºä¸Ģ个
    0.19
    èĶļ
    0.19
    ä¸įæĿ¥
    0.19
    sto
    0.18
    Activations Density 0.235%

    No Known Activations