© 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. 16777
    Prev
    Next
    INDEX
    Explanations

    geology, geophysics, scientist

    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
    åĮ»çĸĹåĻ¨æ¢°
    -0.20
    воÑĢ
    -0.20
    樾
    -0.20
     Geile
    -0.20
    åİ®
    -0.20
     STREET
    -0.19
    è¡į
    -0.19
    zeÅĦ
    -0.19
    éłĵ
    -0.19
     healthcare
    -0.19
    POSITIVE LOGITS
    åľ°è´¨
    0.39
    åľ°çIJĥ
    0.37
     Earth
    0.34
    åľ°è²Į
    0.30
    Earth
    0.28
    å²©çŁ³
    0.28
    大æ°Ķ
    0.28
     scientists
    0.27
    ç§ijåŃ¦å®¶
    0.27
    åĭĺæİ¢
    0.26
    Activations Density 0.065%

    No Known Activations