© 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. 16512
    Prev
    Next
    INDEX
    Explanations

    disappeard disappeared during

    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
    èµĭäºĪ
    -0.25
    éĩįçĤ¹
    -0.24
     ninete
    -0.24
    建ç«ĭ
    -0.24
     C
    -0.23
    樱æ¡ĥ
    -0.23
     B
    -0.23
    F
    -0.23
    (
    -0.23
     collegiate
    -0.23
    POSITIVE LOGITS
    åħ¨æĿij
    0.26
    ONTAL
    0.25
    æĿijéĩĮ
    0.25
    åĽłä¸ºä»ĸ们
    0.24
    ibia
    0.24
    ParallelGroup
    0.23
    ãng
    0.23
    aleb
    0.23
    zá
    0.23
    èį®
    0.23
    Activations Density 0.042%

    No Known Activations