© 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. 13180
    Prev
    Next
    INDEX
    Explanations

    flour or cheese

    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
    llib
    -0.21
    åħļåĴĮæĶ¿åºľ
    -0.21
    chemes
    -0.20
    edException
    -0.20
    èµ·çłģ
    -0.19
    å¤ĸè´¸
    -0.19
    éļ¾è¿ĩ
    -0.18
    åħ´æĹº
    -0.18
    Filled
    -0.18
     Essentials
    -0.18
    POSITIVE LOGITS
    ç²¾éĢī
    0.27
    é¢łè¦Ĩ
    0.22
    å¾½
    0.20
    åĪ¶ä½ľ
    0.19
     quint
    0.19
    交äºĴ
    0.19
    éķľ
    0.19
    _mas
    0.19
    碰æĴŀ
    0.18
     Triple
    0.18
    Activations Density 0.010%

    No Known Activations