© 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. 15278
    Prev
    Next
    INDEX
    Explanations

    numeric quantities or counts

    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
    äºĶçĻ¾
    -0.30
    ä¸īåįĥ
    -0.28
    两åįĥ
    -0.27
    ä¸Ģåįĥ
    -0.26
    åĩłåįĥ
    -0.24
    åįģä¸ĩ
    -0.24
    è¿ijåįĥ
    -0.24
     millions
    -0.23
     thousands
    -0.23
    äºĶåįĥ
    -0.22
    POSITIVE LOGITS
    ä¸Ģ个å°ı
    0.26
    两åIJį
    0.26
    ä¿©
    0.26
    æľī两个
    0.26
    æľīåĩłä¸ª
    0.26
     два
    0.24
     two
    0.24
    åıªæľīä¸Ģ个
    0.23
     one
    0.23
    ä¸Ģãģ¤
    0.23
    Activations Density 0.308%

    No Known Activations