© 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. 16783
    Prev
    Next
    INDEX
    Explanations

    Right just true art big industry equal

    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
    æľ¬åĽ½
    -0.20
    èı°
    -0.20
     Hearts
    -0.19
    绿水
    -0.19
     Tatto
    -0.19
    ********************************************************************************
    -0.19
    bmp
    -0.19
    ocks
    -0.19
    æīĭéĩĮ
    -0.18
    年产åĢ¼
    -0.18
    POSITIVE LOGITS
    âĦ¢
    0.28
    (TM
    0.25
    (tm
    0.23
     âĸĪ
    0.20
    inan
    0.20
    äºĭåĦ¿
    0.20
    zee
    0.20
     Thing
    0.19
    ®
    0.19
    Thing
    0.19
    Activations Density 0.075%

    No Known Activations