© 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. 15939
    Prev
    Next
    INDEX
    Explanations

    genres like action and thriller

    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
    flat
    -0.21
    éĶµ
    -0.21
    mas
    -0.20
    åĿļ
    -0.19
    æīģ
    -0.19
    贯穿
    -0.18
    èIJ¦
    -0.18
    èĪIJ
    -0.18
    unte
    -0.18
    ater
    -0.17
    POSITIVE LOGITS
    achi
    0.20
    Thr
    0.19
    prüf
    0.18
    æĿĤè´¨
    0.18
    æľªçŁ¥
    0.18
    THR
    0.18
    -ajax
    0.17
    人åĬĽèµĦæºIJ
    0.17
    apore
    0.17
    och
    0.17
    Activations Density 0.005%

    No Known Activations