© 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. 16735
    Prev
    Next
    INDEX
    Explanations

    figure out / get out / get it

    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
     ÑĢей
    -0.20
    ä¸įè¿ľ
    -0.20
    oola
    -0.20
    RICT
    -0.20
    æľīä¸Ģå®ļ
    -0.19
    знак
    -0.19
    avery
    -0.18
    anded
    -0.18
    衲
    -0.18
    ê¹ħ
    -0.18
    POSITIVE LOGITS
    ä¹ŁæĹłæ³ķ
    0.28
    æī¾ä¸įåĪ°
    0.25
     anything
    0.24
    éĥ½æĹłæ³ķ
    0.23
    ä¸Ŀ毫
    0.23
     anymore
    0.21
     EVER
    0.20
    æĹłæ³ķ
    0.20
    æ¿ĢåĬ¨
    0.20
     ná»ķi
    0.20
    Activations Density 0.160%

    No Known Activations