© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 27
    Prev
    Next
    INDEX
    Explanations

    explaining a reason

    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
    -0.25
    èĢĮéĿŀ
    -0.23
    建议
    -0.23
    edly
    -0.22
    åĽłèĢĮ
    -0.20
    缸åĬ©
    -0.20
    ãģĹãģ¾ãģĦ
    -0.19
    为æĤ¨
    -0.19
    åħ¬çº¦
    -0.19
    thus
    -0.19
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.30
    ä»Ģä¹ĪåİŁåĽł
    0.27
    å®ĥ们
    0.24
    å®ĥæĺ¯
    0.22
     nó
    0.22
    åįķ纯çļĦ
    0.21
     they
    0.21
    igned
    0.21
     there
    0.21
     it
    0.21
    Activations Density 0.055%

    No Known Activations