© 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. 15417
    Prev
    Next
    INDEX
    Explanations

    independent entities and affiliations

    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
    åŁİéĩĮ
    -0.21
     акÑĤÑĥ
    -0.20
    å¤ı天
    -0.20
    _BL
    -0.19
    emple
    -0.19
    _nsec
    -0.18
    主åħ¬
    -0.18
    失ä¸ļ
    -0.18
    ç¯Ħ
    -0.18
     ме
    -0.18
    POSITIVE LOGITS
    çĭ¬ç«ĭ
    0.50
    çį¨ç«ĭ
    0.41
     independent
    0.36
    Independent
    0.35
     independ
    0.34
     Independent
    0.34
    ä¸į代表
    0.29
     independently
    0.29
    èĩªä¸»
    0.28
     independence
    0.26
    Activations Density 0.018%

    No Known Activations