© 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. 13289
    Prev
    Next
    INDEX
    Explanations

    sodium and chloride transport

    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
    è¹Ī
    -0.20
    é³ķ
    -0.18
    è··
    -0.17
    åĶ§
    -0.17
    è°ħ解
    -0.17
    å¼Ł
    -0.17
    èĤ´
    -0.17
    çݳ
    -0.17
    绳
    -0.16
    åı¤æĢª
    -0.16
    POSITIVE LOGITS
    rine
    0.18
    utilus
    0.18
    ValueChanged
    0.17
    ÙĬات
    0.17
    éĻ©
    0.17
    æ°ı
    0.16
    常
    0.16
    -rich
    0.16
    æ¯ıå¹´éĥ½
    0.16
     Architects
    0.15
    Activations Density 0.021%

    No Known Activations