© 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. 13796
    Prev
    Next
    INDEX
    Explanations

    candle and oil burning

    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
    裤åŃIJ
    -0.20
    èĥ±
    -0.20
    褲
    -0.20
    é«ĺåİĭ
    -0.19
    outh
    -0.19
    akit
    -0.19
    tail
    -0.19
    çľģæķĻèĤ²
    -0.19
    æ¶İ
    -0.19
    owo
    -0.19
    POSITIVE LOGITS
     candle
    0.33
     candles
    0.33
    èľ¡
    0.29
    çĤ·
    0.27
    çĤī
    0.26
    çĥĽ
    0.25
     burn
    0.24
    aison
    0.23
     Candle
    0.22
    çĩĥ
    0.22
    Activations Density 0.004%

    No Known Activations