© 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. 14086
    Prev
    Next
    INDEX
    Explanations

    word endings like 'ions'

    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
    ÂŃs
    -0.20
    çļĦç¡®
    -0.19
    èIJ¼
    -0.19
    plied
    -0.19
    ä¸ĢåĪĨ
    -0.19
    æķĿ
    -0.18
    ãĢħ
    -0.18
    IgnoreCase
    -0.18
    åIJ¦è®¤
    -0.18
    press
    -0.17
    POSITIVE LOGITS
    ally
    0.23
    Ìģ
    0.20
    ALLY
    0.19
    ovies
    0.19
    ció
    0.19
    ional
    0.18
    [out
    0.17
    asca
    0.17
    oftware
    0.17
    Åķ
    0.17
    Activations Density 1.313%

    No Known Activations