© 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. 501
    Prev
    Next
    INDEX
    Explanations

    is that / is how

    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
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.26
    æĪIJåĬŁ
    -0.26
    /ec
    -0.23
    çļĦä¸Ģ项
    -0.23
    etri
    -0.23
    arty
    -0.22
    注æĦıåĪ°
    -0.21
    æīĢåľ¨çļĦ
    -0.21
    èĩªèº«
    -0.21
    AREN
    -0.21
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.37
    äºĽä»Ģä¹Ī
    0.26
    è¦ģä¹Ī
    0.26
    è°ģèĥ½
    0.25
     Either
    0.24
    åıªæľīä¸Ģ个
    0.24
    å¦ĤæŀľæĪij们
    0.24
     nothing
    0.23
     whether
    0.23
     Obviously
    0.23
    Activations Density 0.088%

    No Known Activations