© 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. 15887
    Prev
    Next
    INDEX
    Explanations

    new frontiers, perspectives, potential, approaches, impact

    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
    vine
    -0.18
    穹
    -0.18
    ret
    -0.18
    Ãłng
    -0.18
    çĴŁ
    -0.18
    oves
    -0.18
    berg
    -0.18
    è¿ĻäºĽ
    -0.17
    çŃīåIJĦç§į
    -0.17
    禧
    -0.17
    POSITIVE LOGITS
     Edition
    0.26
    ãģ§ãģĻãģĭ
    0.20
    说ä»Ģä¹Ī
    0.19
    wik
    0.19
     Www
    0.18
    _MUX
    0.18
    é¹ħ
    0.18
    esti
    0.18
    æĬij
    0.18
    åģļä»Ģä¹Ī
    0.18
    Activations Density 0.433%

    No Known Activations