© 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. 14032
    Prev
    Next
    INDEX
    Explanations

    Lego construction blocks

    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
    æīĵå·¥
    -0.19
    åľºæīĢ
    -0.18
    åŁ
    -0.18
    æ±²
    -0.18
    çĶ¨çĶµ
    -0.18
    æĺĤ
    -0.18
    onta
    -0.18
    åı£æ°Ķ
    -0.18
    æ²¼
    -0.17
    æģ
    -0.17
    POSITIVE LOGITS
    ç¢İçīĩ
    0.22
     puzzle
    0.21
    ä¹ĭ家
    0.21
    uzzle
    0.21
    åĦ¿
    0.21
    ä¸Ģæŀļ
    0.21
     pieces
    0.20
    çĽĴ
    0.20
    æĶ¾ä¸ĭ
    0.20
     grains
    0.19
    Activations Density 0.027%

    No Known Activations