© 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. 13321
    Prev
    Next
    INDEX
    Explanations

    demographics and groups

    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
    çļĦåĵģçīĮ
    -0.19
    é½IJé²ģ
    -0.19
    åıĸåĨ³äºİ
    -0.18
    æīİ
    -0.18
    Eye
    -0.18
     Spirits
    -0.18
    ä¼ĺ
    -0.18
    çħ§æł·
    -0.18
    AIT
    -0.18
     eye
    -0.18
    POSITIVE LOGITS
    subtype
    0.20
     subtype
    0.20
    å´
    0.19
    鸽
    0.19
     shaved
    0.19
    DataReader
    0.19
    stan
    0.19
    çĶ³
    0.19
    esk
    0.18
    URN
    0.18
    Activations Density 0.898%

    No Known Activations