© 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. 11571
    Prev
    Next
    INDEX
    Explanations

    motivation

    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
    -quarters
    -0.17
    pter
    -0.17
    alık
    -0.17
    æ·ĩ
    -0.17
    nge
    -0.16
    éľģ
    -0.16
    ociety
    -0.16
    Å¡t
    -0.16
    owing
    -0.16
    ÙĪات
    -0.15
    POSITIVE LOGITS
    ally
    0.24
    åįģ足
    0.24
    æĢ§å¼º
    0.20
    ALLY
    0.20
    ä»ĺãģij
    0.19
    ted
    0.19
    éĿŀåĩ¡
    0.19
    less
    0.19
    -driven
    0.18
    æĪijåİ»
    0.18
    Activations Density 0.015%

    No Known Activations