© 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. 16823
    Prev
    Next
    INDEX
    Explanations

    and followed by word

    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
    nees
    -0.19
    EPS
    -0.19
    illin
    -0.18
    ointed
    -0.18
    æ³£
    -0.18
    泪水
    -0.17
    äºĭåIJİ
    -0.17
    quee
    -0.16
    aÄŁ
    -0.16
    _linux
    -0.16
    POSITIVE LOGITS
    åħħå®ŀ
    0.27
    èĢĮæĿ¥
    0.25
    èĢĮæĪIJ
    0.24
    è¿ĽæĿ¥
    0.23
    è¡¥åħħ
    0.22
    ç²¹
    0.22
    åĬłä¸Ĭ
    0.22
    à¸Ļำมา
    0.21
    转åĮĸ为
    0.21
    come
    0.21
    Activations Density 0.343%

    No Known Activations