© 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. 12839
    Prev
    Next
    INDEX
    Explanations

    US senators and politicians

    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
    ä¾µçķ¥
    -0.20
    íĻĢ
    -0.20
    âĩ
    -0.19
    æİ¢
    -0.19
    箫
    -0.19
    èĦ¯
    -0.19
    ä»ĸå¦Ī
    -0.19
    诡
    -0.19
    Meter
    -0.18
    ify
    -0.18
    POSITIVE LOGITS
    gary
    0.24
    裸
    0.23
    neutral
    0.21
     neutral
    0.20
     neut
    0.20
    aise
    0.20
    绣æĪĺ
    0.19
    abay
    0.19
    ldb
    0.19
    åIJİæĤĶ
    0.19
    Activations Density 0.011%

    No Known Activations