© 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. 15217
    Prev
    Next
    INDEX
    Explanations

    religious figures and organizations

    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
    ity
    -0.21
    ĮĢ
    -0.19
    eting
    -0.18
    овоÑĢ
    -0.18
    æİ©çĽĸ
    -0.18
     trữ
    -0.18
    模ç³Ĭ
    -0.17
    åĢĴåľ¨
    -0.17
    setQuery
    -0.17
    combe
    -0.17
    POSITIVE LOGITS
    èĢħ
    0.19
    ìĽIJ
    0.19
    ìļĶ
    0.18
     Mission
    0.18
    涯
    0.18
    igos
    0.17
    å¸Ī
    0.17
    師
    0.17
     Trainer
    0.17
    伸
    0.16
    Activations Density 0.002%

    No Known Activations