© 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. 14051
    Prev
    Next
    INDEX
    Explanations

    multi-in-one

    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
    é¢ļ
    -0.20
     handheld
    -0.17
     substant
    -0.17
    鸬
    -0.17
    è¿ĻåĦ¿
    -0.17
    ä¸Ģç¬ij
    -0.17
    ìķ¼
    -0.17
    Mayor
    -0.17
     withholding
    -0.17
    ĭ
    -0.17
    POSITIVE LOGITS
    ä¸ĭæ²ī
    0.22
     Drum
    0.21
    åŀĭ
    0.20
    éĽĨä¸Ń
    0.20
    apos
    0.19
    丰å¯Įå¤ļ彩
    0.19
    åħ¬å¼Ģåıij
    0.18
    éĢłåŀĭ
    0.18
    Fonts
    0.17
     DIAG
    0.17
    Activations Density 0.003%

    No Known Activations