© 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. 16630
    Prev
    Next
    INDEX
    Explanations

    institutions or organizations

    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
    åĬŁå¤«
    -0.18
    arris
    -0.18
    enos
    -0.17
    andre
    -0.17
    çŃīæĸ¹éĿ¢çļĦ
    -0.17
     underneath
    -0.17
    ä¸į失
    -0.16
    æħİ
    -0.16
     undert
    -0.16
     chan
    -0.16
    POSITIVE LOGITS
    æĿ¥è®²
    0.24
    çļĦ人æĿ¥è¯´
    0.21
    .serialization
    0.21
    æĿ¥è¯´
    0.20
     Til
    0.19
    çľĭä¸įåĪ°
    0.18
    åı¯ä»¥çľĭåĩº
    0.18
    åİĦ
    0.18
    ä¾Ĩ說
    0.18
    aña
    0.17
    Activations Density 0.312%

    No Known Activations