© 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. 13824
    Prev
    Next
    INDEX
    Explanations

    Cartesian join, product, gland

    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
    åħħ
    -0.20
    æĸ°ä¸ī
    -0.19
    robe
    -0.19
    _STRIP
    -0.19
     strips
    -0.18
    PEAT
    -0.18
    åŁĭ
    -0.18
    大æ°Ķ
    -0.17
    ((__
    -0.17
    åīį线
    -0.17
    POSITIVE LOGITS
    çķ¥
    0.22
     mach
    0.19
    çķ¥å¾®
    0.19
    еле
    0.18
     luk
    0.18
    ä½ĵéªĮ
    0.18
    æĿ¥ä¸įåıĬ
    0.18
     mom
    0.17
    ales
    0.17
    ì¶ķ
    0.17
    Activations Density 0.001%

    No Known Activations