© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16981
    Prev
    Next
    INDEX
    Explanations

    wet lab, wet bulb, wetness, wetlands

    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
    ively
    -0.21
    ses
    -0.17
    ael
    -0.17
    ober
    -0.17
    sse
    -0.17
    sic
    -0.16
    iller
    -0.16
    ero
    -0.16
    ously
    -0.15
    umed
    -0.15
    POSITIVE LOGITS
    ters
    0.26
    ening
    0.25
    lands
    0.23
    ness
    0.23
    inary
    0.22
    ting
    0.20
    desk
    0.19
    ted
    0.18
    onomy
    0.18
    tk
    0.17
    Activations Density 0.004%

    No Known Activations