© 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. 14726
    Prev
    Next
    INDEX
    Explanations

    first team appearance

    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
    ynes
    -0.22
    å¾ĪæŃ£å¸¸
    -0.19
    pter
    -0.19
     polarity
    -0.19
     Gest
    -0.18
    ÑģпеÑĪ
    -0.18
    åľ¨ç½ij绾
    -0.18
    åĬŀ好
    -0.17
    åľ¨ç½ijä¸Ĭ
    -0.17
    äºĨä¸Ģ声
    -0.17
    POSITIVE LOGITS
     tÆ°
    0.19
    æĿĥå¨ģ
    0.19
     SHIFT
    0.18
    ers
    0.18
    ä¸ŃåİŁ
    0.18
    edly
    0.18
    èĪĽ
    0.18
    两çĤ¹
    0.18
    iens
    0.18
    amen
    0.18
    Activations Density 0.002%

    No Known Activations