© 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. 11783
    Prev
    Next
    INDEX
    Explanations

    non-Latin script characters

    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
    æ´Ĺæīĭ
    -0.25
    伸æīĭ
    -0.22
    ç½ijåıĭè¯Ħ论
    -0.21
    å¹´ä¹ĭ
    -0.19
    æĪij没æľī
    -0.19
    ä¸įæĺ¯
    -0.19
    çĶµåĻ¨
    -0.19
    说çļĦæĺ¯
    -0.18
    没æľī人
    -0.18
    éĽı
    -0.18
    POSITIVE LOGITS
    ilent
    0.23
    â
    0.21
    áo
    0.20
    [](
    0.20
    WithType
    0.19
     Leslie
    0.19
    antu
    0.19
    ephy
    0.19
    emble
    0.19
    家纺
    0.19
    Activations Density 0.102%

    No Known Activations