© 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. 13704
    Prev
    Next
    INDEX
    Explanations

    tour dates and locations

    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
    çİĭåĽ½
    -0.22
    ãģĻãģ¹
    -0.20
    æĹ¥å¸¸å·¥ä½ľ
    -0.20
    æĬĵ好
    -0.20
    汩
    -0.19
    atron
    -0.18
    actory
    -0.18
    busters
    -0.18
    amily
    -0.18
    boot
    -0.18
    POSITIVE LOGITS
    åIJĮ缣
    0.21
    çĻ»
    0.21
    -ending
    0.21
    æĥħ
    0.20
    å§ĭäºİ
    0.20
    _STARTED
    0.19
    çģ«çĤ¬
    0.18
     mol
    0.17
    ä»ħ次äºİ
    0.17
    è¿ĩç¨ĭ
    0.17
    Activations Density 0.003%

    No Known Activations