© 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. 14082
    Prev
    Next
    INDEX
    Explanations

    oil, gas, drilling, offshore

    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
    åºŃéĻ¢
    -0.22
    ivic
    -0.21
    èī²ç´ł
    -0.21
    erg
    -0.20
    school
    -0.19
    å¸ĪèĮĥ
    -0.19
    illus
    -0.19
    éħIJ
    -0.19
    erras
    -0.19
    èī²
    -0.19
    POSITIVE LOGITS
    æµ·ä¸Ĭ
    0.35
    æ²¹æ°Ķ
    0.30
     offshore
    0.30
    ä½ľä¸ļ
    0.26
    æ²¹çĶ°
    0.25
     اÙĦØ®ÙĦÙĬج
    0.24
    渤
    0.24
     LNG
    0.23
     Exxon
    0.23
    渤海
    0.23
    Activations Density 0.102%

    No Known Activations