© 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. 16816
    Prev
    Next
    INDEX
    Explanations

    system / apparatus names

    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
    achs
    -0.20
    usan
    -0.20
    缯
    -0.19
    åijĽ
    -0.19
    主æĿĥ
    -0.19
    anean
    -0.18
    éļĺ
    -0.18
    SupportedContent
    -0.18
    éĨº
    -0.18
    ðŁİĵ
    -0.18
    POSITIVE LOGITS
    èµĸ以
    0.23
    -based
    0.22
    -like
    0.22
    ç³»ç»ŁçļĦ
    0.21
    使çĶ¨çļĦ
    0.21
    æĪĸå¤ļ
    0.20
    -style
    0.20
     system
    0.19
    æīĭ游
    0.19
    åºĬä¸Ĭ
    0.18
    Activations Density 0.832%

    No Known Activations