© 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. 12136
    Prev
    Next
    INDEX
    Explanations

    to the

    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
    alli
    -0.19
    åģļçļĦäºĭæĥħ
    -0.19
    ãģĹãģŁãĤĤãģ®
    -0.19
    alle
    -0.19
    æ»Ķ
    -0.18
    throp
    -0.18
     peg
    -0.18
     vẻ
    -0.18
    åĵī
    -0.18
    åŁºæľ¬ä¸Ĭ
    -0.18
    POSITIVE LOGITS
    ä¹ĭä¸Ń
    0.22
    人身
    0.20
    ä¹ĭ人
    0.19
    å
    0.19
    èĻļåģĩ
    0.19
    两ä¼ļ
    0.18
    gom
    0.18
    >manual
    0.18
    åħ¨å¥Ĺ
    0.18
    æľ¬åĽ½
    0.18
    Activations Density 0.094%

    No Known Activations