© 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. 14482
    Prev
    Next
    INDEX
    Explanations

    marriage and relationships

    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
    æ´»åĬ¨
    -0.22
    以便
    -0.22
     Fare
    -0.22
    å°ĸ
    -0.21
    碰
    -0.20
    ä¸Ģä¼ļåĦ¿
    -0.20
    ä¸Ģä¼ļ
    -0.20
    åįĬ天
    -0.20
    éĩįçĤ¹åħ³æ³¨
    -0.20
     activity
    -0.19
    POSITIVE LOGITS
    å½ĵåĪĿ
    0.24
    _TypeDef
    0.23
    çļĦçĪ±æĥħ
    0.23
    åľ¨ä¸Ģèµ·
    0.23
    åIJĮå¹´
    0.23
     union
    0.23
    .union
    0.22
     unions
    0.22
    union
    0.21
    çĪ±æĥħ
    0.21
    Activations Density 0.029%

    No Known Activations