© 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. 11501
    Prev
    Next
    INDEX
    Explanations

    direction and orientation

    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
    åĴĮå®ĮåĸĦ
    -0.20
    ä¸ĩåĪĨ
    -0.20
    åĹ²
    -0.19
    æİĴ骨
    -0.19
    åĵį
    -0.19
    éĨª
    -0.18
    arians
    -0.18
    趿
    -0.18
     matrimon
    -0.18
    èģĶåĬ¨
    -0.18
    POSITIVE LOGITS
    éĿ¢åIJij
    0.22
    ISCO
    0.22
    æľīä¸Ģ
    0.21
    -facing
    0.21
    å±ĢéĿ¢
    0.20
    wards
    0.20
    æĸ¹åIJij
    0.20
    èĢĮä¸įæĺ¯
    0.20
    çļĦå±ĢéĿ¢
    0.20
     MessageType
    0.20
    Activations Density 0.048%

    No Known Activations