© 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. 16306
    Prev
    Next
    INDEX
    Explanations

    to make / to fulfill / to grow

    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
    åĦ¿
    -0.21
    éĤ£äºĽ
    -0.20
    çļĦæĺ¯
    -0.20
    çļĦ对象
    -0.20
    å¼ıçļĦ
    -0.19
    éĻĽä¸ĭ
    -0.18
    们
    -0.18
    rad
    -0.18
    çļĦ人æĿ¥è¯´
    -0.18
    met
    -0.17
    POSITIVE LOGITS
    alic
    0.20
    éĿŀ常好
    0.19
    tas
    0.17
    LastError
    0.17
     dors
    0.16
    omba
    0.16
     herd
    0.16
    Biz
    0.16
    çľĭä¸Ģçľĭ
    0.15
    Argb
    0.15
    Activations Density 0.052%

    No Known Activations