© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14903
    Prev
    Next
    INDEX
    Explanations

    writing essay thesis adapters Node data Category

    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
     Palestin
    -0.26
    å®Į
    -0.24
    ÑĩÑĢежден
    -0.21
    медиÑĨинÑģк
    -0.21
    ago
    -0.20
     Belg
    -0.20
    éĩįè¦ģ
    -0.19
    è®°å½ķ
    -0.19
    over
    -0.19
    ble
    -0.19
    POSITIVE LOGITS
     nuru
    0.22
    游æĪı代
    0.22
    sic
    0.20
    åľ¨çݩ家ä¸Ń
    0.20
    æĸ¹åľĨ
    0.20
    åģıåģı
    0.20
    çªģå¦Ĥ
    0.20
     wida
    0.19
    è¿Ļæł·çļĦè¯Ŀ
    0.19
    'gc
    0.19
    Activations Density 0.023%

    No Known Activations