© 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. 14335
    Prev
    Next
    INDEX
    Explanations

    religious texts translation

    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
    à¤ĺ
    -0.23
     Geile
    -0.21
    çĶ©
    -0.20
     [-]:
    -0.19
    çŃ
    -0.19
    Documentation
    -0.19
    æµģæĺŁ
    -0.19
     Documentation
    -0.19
    /photos
    -0.19
    eldon
    -0.19
    POSITIVE LOGITS
    çīĪæľ¬
    0.45
     version
    0.34
     versions
    0.30
    æł¼å¼ı
    0.28
    æĿĥå¨ģ
    0.27
    对çħ§
    0.26
    修订
    0.26
    çīĪ
    0.25
    éĢIJ
    0.25
     editions
    0.24
    Activations Density 0.063%

    No Known Activations