© 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. 16022
    Prev
    Next
    INDEX
    Explanations

    part of project names

    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
    ä»Ģä¹Īåij¢
    -0.21
    inals
    -0.21
    å®Ĺ
    -0.21
    inal
    -0.20
    ç«ĭæ¡Ī
    -0.20
    æ³ķ令
    -0.20
    FINAL
    -0.20
    ç«ĭéĿ¢
    -0.20
    å¼¹
    -0.19
    Bas
    -0.19
    POSITIVE LOGITS
    .pet
    0.22
    loe
    0.21
    èıŁ
    0.20
     Ivy
    0.20
    icut
    0.19
    pet
    0.19
    LOB
    0.19
     걸
    0.19
     Grat
    0.19
    خد
    0.18
    Activations Density 0.133%

    No Known Activations