© 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. 15847
    Prev
    Next
    INDEX
    Explanations

    fashion, bespoke, designer

    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
    dia
    -0.20
    ëĭĿ
    -0.19
    æīĵçIJĥ
    -0.19
     Musical
    -0.18
    çĿĢæīĭ
    -0.18
    ç«ĭãģ¡
    -0.18
    agra
    -0.17
    两æĿ¡
    -0.17
    ä¼Ļä¼´åħ³ç³»
    -0.17
    ousse
    -0.17
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.24
    ulous
    0.23
    (dy
    0.21
    级
    0.21
    人士
    0.20
    æĦıä¹īä¸ĬçļĦ
    0.20
    å·¥ä½ľå®¤
    0.20
    iat
    0.19
    phere
    0.19
    èĪ¬çļĦ
    0.19
    Activations Density 0.005%

    No Known Activations