© 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. 11770
    Prev
    Next
    INDEX
    Explanations

    events before actions

    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
    çļĦçIJĨçĶ±
    -0.22
    ä¹Łå¥½
    -0.21
    æ±ķ
    -0.20
    èĢĮä¸Ķè¿ĺ
    -0.20
    maal
    -0.19
    ä¸įè¦ģåĨį
    -0.19
    ä¸įä»ħè¦ģ
    -0.19
    çļĦç¼ĺæķħ
    -0.19
    implicitly
    -0.19
    åĽºçĦ¶
    -0.19
    POSITIVE LOGITS
    æľĢç»Ī
    0.30
    åIJİæĿ¥
    0.27
     eventually
    0.27
     eventual
    0.27
    å°Ĩåħ¶
    0.24
    æľĢçµĤ
    0.24
     finally
    0.24
     later
    0.23
    转åħ¥
    0.22
    æľĢåIJİ
    0.21
    Activations Density 0.032%

    No Known Activations