© 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. 16031
    Prev
    Next
    INDEX
    Explanations

    Hunter Oaks, STROLLER, I'm, sophisticated

    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
    æĺ¨
    -0.20
    unt
    -0.18
    fit
    -0.18
    åĽłåľ°
    -0.18
    iken
    -0.18
     unt
    -0.18
    驳
    -0.17
    kowski
    -0.17
    éķIJ
    -0.17
    arring
    -0.17
    POSITIVE LOGITS
     Lastly
    0.24
     finally
    0.23
    Lastly
    0.20
    è¿ĺæľīä¸Ģ个
    0.20
     Finally
    0.19
    åı¦å¤ĸä¸Ģ个
    0.18
    åĢĴæĺ¯
    0.18
     обÑıзаÑĤелÑĮ
    0.18
    è¿Ļä¸ĢåĪĩ
    0.18
    ä¹Łå¸ĮæľĽ
    0.18
    Activations Density 0.074%

    No Known Activations