© 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. 16150
    Prev
    Next
    INDEX
    Explanations

    mass with following words

    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
    ../../
    -0.22
    ../../../
    -0.20
    ture
    -0.18
     midst
    -0.17
    CTION
    -0.17
    ../../../../
    -0.17
    thal
    -0.17
    说æĺ¯
    -0.16
    èįīæ¡Ī
    -0.15
    ÑĤÑı
    -0.15
    POSITIVE LOGITS
    ively
    0.29
    achusetts
    0.26
    ses
    0.26
    achuset
    0.24
    iveness
    0.21
    åĮĸçļĦ
    0.21
    ing
    0.20
    ignment
    0.20
    imo
    0.20
    aging
    0.19
    Activations Density 0.031%

    No Known Activations