© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15339
    Prev
    Next
    INDEX
    Explanations

    review of Japanese literature

    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
     bó
    -0.24
     воÑĤ
    -0.22
    gaard
    -0.19
    à¸ī
    -0.19
     вок
    -0.19
    訾
    -0.18
    manent
    -0.17
    urate
    -0.17
    fas
    -0.17
    éĤ
    -0.17
    POSITIVE LOGITS
    åħ¶ä»ĸ
    0.24
    èijĹåIJįçļĦ
    0.23
    åħ¼
    0.22
    åıįè¿ĩæĿ¥
    0.22
    åħ¶ä»ĸçļĦ
    0.22
    缸åħ³çļĦ
    0.21
    åħ¶å®ĥ
    0.21
    缸åħ³
    0.20
    åħ¶ä»ĸ人
    0.20
    çļĦ缸åħ³
    0.20
    Activations Density 0.122%

    No Known Activations