© 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. 1259
    Prev
    Next
    INDEX
    Explanations

    ranges or quantities

    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
    åĴĮ
    -0.31
    åĴĮ个人
    -0.29
    åĴĮ社ä¼ļ
    -0.29
    åĴĮåħ¶ä»ĸ
    -0.26
    -xl
    -0.25
    ãĢģ
    -0.25
    åĴĮæĬĢæľ¯
    -0.24
    åĴĮä»ĸçļĦ
    -0.24
    æĢ§åĴĮ
    -0.24
     and
    -0.23
    POSITIVE LOGITS
    depending
    0.55
     depending
    0.53
    Depending
    0.43
     Depending
    0.39
    ãģĦãģļãĤĮ
    0.30
    åıĸåĨ³äºİ
    0.28
    åĽĽäºĶ
    0.28
     whichever
    0.28
     alike
    0.27
    ija
    0.26
    Activations Density 0.100%

    No Known Activations