© 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. 14990
    Prev
    Next
    INDEX
    Explanations

    Honorable titles

    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
    å°½éĩı
    -0.20
    æ»ļåĬ¨
    -0.19
    éĺī
    -0.19
    ëĦ¤
    -0.18
    ä¸Ģç»ı
    -0.18
    åĨ¬å¤©
    -0.18
    妮
    -0.18
    好æĦŁ
    -0.17
    éĻ©
    -0.17
     economy
    -0.17
    POSITIVE LOGITS
     Sir
    0.22
     اÙĦسÙĬد
    0.21
    cue
    0.20
    _sensitive
    0.19
    产åѦçłĶ
    0.19
     Mr
    0.19
    shed
    0.19
    istrate
    0.19
     Shack
    0.19
     Worldwide
    0.18
    Activations Density 0.042%

    No Known Activations