© 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. 14143
    Prev
    Next
    INDEX
    Explanations

    one or more people

    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
    éĢĶ
    -0.24
    å¥Ī
    -0.22
    åij¨è¾¹
    -0.21
    æĤ¬
    -0.20
     Paran
    -0.20
    æµ·å¤ĸ
    -0.20
    åIJĬ
    -0.19
    ç£ķ
    -0.19
    好åIJĥ
    -0.19
    éĿ©æĸ°
    -0.19
    POSITIVE LOGITS
    两个人
    0.23
    ault
    0.21
    ä¸Ģé¡¿
    0.21
    åħ±åIJĮåĬªåĬĽ
    0.20
    ä¸Ģæĸ¹
    0.20
    .OneToOne
    0.20
    两人
    0.19
    yme
    0.19
    ilee
    0.19
     Compatible
    0.19
    Activations Density 0.007%

    No Known Activations