© 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. 1226
    Prev
    Next
    INDEX
    Explanations

    containers for liquids or food

    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
    踩
    -0.24
     comprom
    -0.24
     BIND
    -0.23
    å¢ŀåĢ¼
    -0.23
    è´¢å¯Į
    -0.22
     wealth
    -0.22
    çģµæĦŁ
    -0.22
    ç¿ħèĨĢ
    -0.21
     acknowled
    -0.21
    éĩİçĶŁåĬ¨çī©
    -0.21
    POSITIVE LOGITS
    容åĻ¨
    0.54
     container
    0.48
     containers
    0.47
    /container
    0.41
    	container
    0.39
    container
    0.39
    -container
    0.36
    æĿ¯åŃIJ
    0.35
    缼
    0.35
    çĽĴåŃIJ
    0.34
    Activations Density 0.066%

    No Known Activations