© 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. 14816
    Prev
    Next
    INDEX
    Explanations

    surrounded by family

    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
    ä»ĭåħ¥
    -0.19
    åĬłåħ¥äºĨ
    -0.19
    åĬłåħ¥
    -0.19
    Comic
    -0.17
    åĮĹè·¯
    -0.17
    éĥ¨åĪĨåĨħ容
    -0.17
    åĢĶ
    -0.17
    ģ
    -0.17
    oppel
    -0.16
    çļĦæĥħ绪
    -0.16
    POSITIVE LOGITS
    çݯç»ķ
    0.31
    åĽĽåij¨
    0.31
    ä¸ĢåľĪ
    0.30
     surrounding
    0.29
    åij¨åĽ´
    0.28
    åĮħåĽ´
    0.25
     surrounded
    0.24
     вокÑĢÑĥг
    0.24
    ä¸Ģ群
    0.24
    åĽ´ç»ķ
    0.23
    Activations Density 0.026%

    No Known Activations