© 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. 15180
    Prev
    Next
    INDEX
    Explanations

    treatment or surgery options

    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
    ENTA
    -0.22
    TestClass
    -0.20
    .sdk
    -0.20
    祧
    -0.20
    Regular
    -0.19
    åħ«åį¦
    -0.19
    å¹³æŶ
    -0.19
    routine
    -0.19
    é»ĦåŁĶ
    -0.19
    ä¼łæŁĵçĹħ
    -0.19
    POSITIVE LOGITS
    æĽ¿ä»£
    0.27
     alternative
    0.23
    ä»£æĽ¿
    0.23
     alternatives
    0.21
    èµ¢
    0.20
    æīĭ段
    0.20
    WEB
    0.20
    åı¯ä»¥éĢīæĭ©
    0.20
    åıĸ代
    0.19
    人éĢī
    0.19
    Activations Density 0.251%

    No Known Activations