© 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. 15556
    Prev
    Next
    INDEX
    Explanations

    Listeria or Barrett's

    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°¼æĸ¯
    -0.26
    åģļ人
    -0.21
    åĪ«
    -0.20
    秦
    -0.19
    éŁ³
    -0.19
    人æīį
    -0.19
    echa
    -0.19
    неÑĢ
    -0.18
    è¿ĩåħ³
    -0.18
    ancode
    -0.18
    POSITIVE LOGITS
    ¢åįķ
    0.23
    éĵİ
    0.19
    ards
    0.18
    读åIJİ
    0.18
    iable
    0.18
    ä½ľèĢħæīĢæľī
    0.18
    iete
    0.18
    ä¸Ģå°ı
    0.17
    åŁºéĩij管çIJĨ
    0.17
    irus
    0.17
    Activations Density 0.005%

    No Known Activations