© 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. 14877
    Prev
    Next
    INDEX
    Explanations

    layer

    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
    thern
    -0.20
    à¸Ľà¸£à¸°à¸Īำ
    -0.19
    /animations
    -0.18
    rait
    -0.18
    ä¼ļåIJĮ
    -0.18
     vib
    -0.17
    kie
    -0.17
    滨
    -0.17
    UMP
    -0.17
    Qui
    -0.17
    POSITIVE LOGITS
     layers
    0.50
    -layer
    0.40
     Layers
    0.39
    å±Ĥ次
    0.39
    層
    0.38
    å±Ĥ
    0.36
    ä¸Ģå±Ĥ
    0.36
     layer
    0.35
    layers
    0.35
    (layers
    0.33
    Activations Density 0.055%

    No Known Activations