© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 785
    Prev
    Next
    INDEX
    Explanations

    "that" followed by verbs, "to" followed by object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     ultimately
    -0.25
    åij¢
    -0.24
    sv
    -0.24
    å§ĭäºİ
    -0.23
    è¿ĩ渡
    -0.23
    åIJĹ
    -0.23
    DetailView
    -0.22
    à¤ł
    -0.22
    æĺ¯å¯¹
    -0.22
    ä¸įåºĶ
    -0.22
    POSITIVE LOGITS
    并å°Ĩ
    0.57
    并
    0.56
    çĦ¶åIJİ
    0.55
    并éĢļè¿ĩ
    0.54
    å¹¶åľ¨
    0.53
    并对
    0.48
    çĦ¶å¾Į
    0.47
    並å°ĩ
    0.46
    并äºİ
    0.44
    并åIJij
    0.43
    Activations Density 0.343%

    No Known Activations