© 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. 13979
    Prev
    Next
    INDEX
    Explanations

    limited use, edition, run, lifetime, quantities, arc

    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
    ../
    -0.23
    ../../
    -0.22
    itian
    -0.20
    INGS
    -0.20
    iness
    -0.19
    ../../../
    -0.18
    fulness
    -0.18
    anson
    -0.18
    ward
    -0.18
    aday
    -0.17
    POSITIVE LOGITS
     rãi
    0.23
    ly
    0.22
     обÑĢазом
    0.21
    æŶéĹ´åĨħ
    0.21
     جدا
    0.20
    tÃł
    0.19
    mente
    0.19
    -sized
    0.19
    ãģĹãģ¾ãģĨ
    0.19
    åĩłå®¶
    0.18
    Activations Density 0.020%

    No Known Activations