© 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. 12738
    Prev
    Next
    INDEX
    Explanations

    glucose metabolism and energy storage

    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
    å¢ĥ
    -0.22
     Yates
    -0.21
    æīĢåľ¨
    -0.20
    åĸĩåıŃ
    -0.19
    åĸī
    -0.19
    ç§ģä¸ĭ
    -0.19
    æĮŀ
    -0.19
    åľ°æĸ¹
    -0.18
    PropertyParams
    -0.18
    èĤ²
    -0.18
    POSITIVE LOGITS
    Stored
    0.30
     stored
    0.28
    stored
    0.26
    转åĮĸ为
    0.22
     starvation
    0.22
    饥饿
    0.22
     stores
    0.21
    åĤ¨å¤ĩ
    0.21
     fuel
    0.21
    èĦĤèĤª
    0.20
    Activations Density 0.065%

    No Known Activations