© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12460
    Prev
    Next
    INDEX
    Explanations

    anti-inflammatory

    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
    èĢ³æľµ
    -0.21
    ultipart
    -0.19
    çļĦç«ŀäºī
    -0.19
    inky
    -0.18
    raising
    -0.18
    [opt
    -0.18
    elters
    -0.17
    oky
    -0.17
     lied
    -0.17
    ogie
    -0.17
    POSITIVE LOGITS
    éĺ²
    0.20
    æģ¯
    0.20
     heat
    0.20
    èĢģåĮĸ
    0.20
    éĢ¾
    0.19
    heat
    0.19
    åĪĬ
    0.19
    лаг
    0.19
    ç²ĺ
    0.18
    è¿ĻäºĽä¸ľè¥¿
    0.18
    Activations Density 0.103%

    No Known Activations