© 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. 11395
    Prev
    Next
    INDEX
    Explanations

    restore, receive, get

    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
    æŃ£åĽłä¸º
    -0.20
     nowhere
    -0.20
    uts
    -0.20
    ä¹ŁæŃ£æĺ¯
    -0.20
     marriages
    -0.19
    ä»ĸèĩªå·±
    -0.19
    ÑĥÑĪки
    -0.19
    祧
    -0.18
    ä»Ģä¹Īåij¢
    -0.18
    nid
    -0.18
    POSITIVE LOGITS
    便åı¯
    0.33
    便ä¼ļ
    0.31
    å°±ä¼ļ
    0.31
    å°±èĥ½
    0.31
    å°±åı¯ä»¥
    0.28
    å°±æľĥ
    0.26
    åį³åı¯
    0.25
    å°±èĥ½å¤Ł
    0.25
    æĪij们就
    0.24
    ä½łä¼ļ
    0.23
    Activations Density 0.024%

    No Known Activations