© 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. 13776
    Prev
    Next
    INDEX
    Explanations

    health symptoms and conditions

    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
    æĶ¾æīĭ
    -0.22
    ifr
    -0.20
    mát
    -0.20
    触åĬ¨
    -0.20
    ×ĵ×£
    -0.20
    å·§
    -0.19
    åįĥä¸ĩ
    -0.19
    ossal
    -0.19
     láºŃp
    -0.19
    éĢĥçĶŁ
    -0.19
    POSITIVE LOGITS
    æĪijçĪ¸
    0.24
    å½ĵæĪij
    0.24
     overall
    0.23
     my
    0.23
    æĪijåıĪ
    0.23
    åĽłä¸ºæĪij
    0.23
    åħ¼é¡¾
    0.23
     myself
    0.23
    ãģªãģıãģªãģ£ãģŁ
    0.23
    Aggregate
    0.22
    Activations Density 0.020%

    No Known Activations