© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17169
    Prev
    Next
    INDEX
    Explanations

    food insecurity and hunger

    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
    Negative Logits
    èĬ±èįī
    -0.22
    墨
    -0.20
    çģ«èĬ±
    -0.20
    豸
    -0.20
    ä¸Ģæīĭ
    -0.19
    åı°
    -0.19
    æ²ī浸
    -0.19
    çݯå¢ĥ污æŁĵ
    -0.19
    FontSize
    -0.18
    éŁ³ä¹IJ
    -0.18
    POSITIVE LOGITS
    ç²®é£Ł
    0.33
    é£Łçī©
    0.29
    ä¾ĽåºĶ
    0.29
    (food
    0.27
    糧
    0.26
    ç²®
    0.26
    ä½ľçī©
    0.26
     food
    0.25
    éĿ¢åĮħ
    0.24
    food
    0.23
    Activations Density 0.025%

    No Known Activations