© 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. 16483
    Prev
    Next
    INDEX
    Explanations

    with the help of

    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
    åĽłä¸ºå®ĥ
    -0.25
    åŃIJéĩĮ
    -0.24
    åĽłä¸ºåľ¨
    -0.24
    åĽłä¸º
    -0.23
    éľĢè¦ģçĶ¨
    -0.21
    åĽłä¸ºæĪij们
    -0.21
    åĽłä¸ºä»ĸ们
    -0.21
    çĶ¨äºĨ
    -0.21
    ä¸İæѤ
    -0.21
    çĶ¨
    -0.21
    POSITIVE LOGITS
    å°±èĥ½
    0.28
    使å¾Ĺ
    0.23
    便åı¯
    0.23
    å°±åı¯ä»¥
    0.23
    ä¸Ģå®ļèĥ½
    0.22
    ä¸įä»ħèĥ½
    0.21
    æĽ´å®¹æĺĵ
    0.20
    æĪijåı¯ä»¥
    0.20
    å®ŀçİ°
    0.20
    度è¿ĩ
    0.20
    Activations Density 0.175%

    No Known Activations