© 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. 16683
    Prev
    Next
    INDEX
    Explanations

    paper and printing materials

    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
     bergen
    -0.21
    htub
    -0.20
    horia
    -0.19
    xit
    -0.19
    é²ĭ
    -0.19
    alla
    -0.18
    ainment
    -0.18
    :length
    -0.18
    -State
    -0.18
    bah
    -0.18
    POSITIVE LOGITS
    纸
    0.38
    ç´Ļ
    0.34
     бÑĥмаг
    0.33
    纸ä¸Ĭ
    0.33
     paper
    0.32
    纸质
    0.27
    paper
    0.27
    åį°åĪ·
    0.26
    éĢłçº¸
    0.26
    ä»ĭè´¨
    0.25
    Activations Density 0.029%

    No Known Activations