© 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. 16396
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    çĪ±ä¸Ĭ
    -0.23
    å½»
    -0.20
    丢äºĨ
    -0.19
    å¼łæī¬
    -0.19
    PathParam
    -0.19
    utra
    -0.19
    åľĥ
    -0.18
    доÑĢож
    -0.18
    acas
    -0.18
    å¼ķè¿Ľ
    -0.18
    POSITIVE LOGITS
     cont
    0.19
    åŃ
    0.18
    PCI
    0.17
    å·¡
    0.17
    éĢĢ
    0.17
    éĶĻ
    0.17
    .setModel
    0.17
     Shard
    0.17
    .pad
    0.16
    ney
    0.16
    Activations Density 0.000%

    No Known Activations