© 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. 16490
    Prev
    Next
    INDEX
    Explanations

    this, is, or what

    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
     swap
    -0.21
    swap
    -0.21
    ä¸Ģäºĭ
    -0.21
    	swap
    -0.20
    檫
    -0.19
    éļIJå½¢
    -0.19
    _swap
    -0.19
    åıįèĢĮ
    -0.18
    éĤ£æł·çļĦ
    -0.18
    çĶŁäºİ
    -0.18
    POSITIVE LOGITS
    ammer
    0.23
    çİ»
    0.20
    ackers
    0.20
    çĿĢæīĭ
    0.20
    表çĻ½
    0.19
    åľ°ä¸Ĭ
    0.19
    kas
    0.18
    åĨł
    0.18
    æ¾Ħ
    0.18
    ä¸į论
    0.17
    Activations Density 0.016%

    No Known Activations