© 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. 11734
    Prev
    Next
    INDEX
    Explanations

    shapes like U, V, W, Y, T

    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
    姿
    -0.19
    coverage
    -0.18
    ouncer
    -0.18
    gia
    -0.18
    afort
    -0.18
    .SetInt
    -0.18
    erais
    -0.18
    [at
    -0.18
    UnderTest
    -0.18
    èĥŃ
    -0.18
    POSITIVE LOGITS
    ç§ĺ书éķ¿
    0.24
    åŀĭ
    0.23
    -shaped
    0.23
    çľ¼è§Ĵ
    0.20
    ç»ĵæŀĦ
    0.20
    å¼ı
    0.20
    ILog
    0.19
     ÅŁeklinde
    0.19
    å½¢
    0.19
    西路
    0.18
    Activations Density 0.015%

    No Known Activations