© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14937
    Prev
    Next
    INDEX
    Explanations

    relative clauses and conjunctions

    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
    вин
    -0.22
    åŀĦ
    -0.20
     esc
    -0.19
    纸ä¸Ĭ
    -0.19
    æ·¡åĮĸ
    -0.19
    éĩįéĩį
    -0.18
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.18
    ény
    -0.18
    ortho
    -0.17
    isci
    -0.17
    POSITIVE LOGITS
    ä¸İæѤ
    0.25
    èIJ¥ä¸ļ
    0.23
    对该
    0.22
    åħ³äºİæĪij们
    0.20
    gh
    0.20
     данном
    0.20
    èIJ¥
    0.19
    åħ³çĪ±
    0.19
    åįıåĬŀ
    0.19
     данного
    0.19
    Activations Density 0.001%

    No Known Activations