© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 15686
    Prev
    Next
    INDEX
    Explanations

    energy, gas, service, bills, connection

    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
     merch
    -0.23
    çľ¼åīį
    -0.22
    æľºåŀĭ
    -0.21
    串
    -0.21
    olds
    -0.20
    æ·¬
    -0.20
    帽
    -0.19
    èĤī
    -0.19
     Merch
    -0.19
     sortie
    -0.18
    POSITIVE LOGITS
    å¥Ĺé¤IJ
    0.27
     services
    0.24
    ä½ıæīĢ
    0.23
     ÑĥÑģлÑĥги
    0.23
     renewal
    0.23
    æĪ·
    0.22
     living
    0.22
    管家
    0.21
    æľįåĬ¡åķĨ
    0.21
     bills
    0.20
    Activations Density 0.023%

    No Known Activations