© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    date and time indicators

    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
    asis
    -0.21
    å¹´åºķ
    -0.21
    å°¤åħ¶æĺ¯
    -0.19
    éĻįä½İæĪIJæľ¬
    -0.19
    éĻĮ
    -0.18
    yt
    -0.18
    lette
    -0.18
    è¹Ĭ
    -0.18
    otten
    -0.18
    ä¼ĹæīĢåij¨çŁ¥
    -0.18
    POSITIVE LOGITS
    éĺµ
    0.24
    èµ·åºĬ
    0.21
    审è§Ĩ
    0.21
    ä¸ĢåĪ»
    0.20
    éĤ£ä¸ĢåĪ»
    0.20
    æѤåĪ»
    0.20
    è¿Ļä¸ĢåĪ»
    0.20
    pmat
    0.20
    åĮĹ京æŶéĹ´
    0.19
    âı°
    0.19
    Activations Density 0.046%

    No Known Activations