© 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. 13270
    Prev
    Next
    INDEX
    Explanations

    Geological Survey

    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
     Labour
    -0.20
     ÅļwiÄĻt
    -0.20
    æĶ¾è¿ĩ
    -0.19
    pitch
    -0.19
    uffy
    -0.19
    é¦ĸ缸
    -0.19
    ello
    -0.18
     Geile
    -0.18
    finance
    -0.18
    yo
    -0.17
    POSITIVE LOGITS
    åľ°ä¸ĭæ°´
    0.23
    ä¿¡æģ¯åħ¬å¼Ģ
    0.23
    åĭĺæŁ¥
    0.23
    岩
    0.23
    å¼ĢåıijåĪ©çĶ¨
    0.23
    åĪĨå±Ģ
    0.23
    åĭĺå¯Ł
    0.21
     hazard
    0.21
    èģĮå·¥
    0.21
     bureau
    0.20
    Activations Density 0.012%

    No Known Activations