© 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. 13381
    Prev
    Next
    INDEX
    Explanations

    social issues and systems

    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
    dro
    -0.18
    eft
    -0.18
    ios
    -0.18
    licence
    -0.17
    .kind
    -0.17
    èļĮ
    -0.17
    æĤ¬
    -0.16
    ld
    -0.16
    æŀ¯
    -0.16
    lang
    -0.16
    POSITIVE LOGITS
    æĢ§å¼º
    0.28
    ilver
    0.18
    åŀ£
    0.18
    çŀ½
    0.17
    åįļä¼ļ
    0.17
    趴
    0.17
     Cro
    0.17
    -themed
    0.17
    _gb
    0.17
     âĵĺ
    0.17
    Activations Density 2.160%

    No Known Activations