© 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. 301
    Prev
    Next
    INDEX
    Explanations

    vice president

    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
    cooked
    -0.29
     kir
    -0.26
    èģĺ请
    -0.25
    kaar
    -0.24
    åºķä¸ĭ
    -0.23
    姨
    -0.23
    åĴĮ个人
    -0.23
    ä¸Ńå°ıåŀĭ
    -0.22
    zsche
    -0.22
    ä»İä¸ļ人åijĺ
    -0.21
    POSITIVE LOGITS
    åĢĻéĢī人
    0.33
    åĢĻéĢī
    0.31
     candidate
    0.31
     candidates
    0.29
    arez
    0.27
    candidate
    0.26
    åī¯
    0.26
     governor
    0.25
    ç«ŀéĢī
    0.24
    人éĢī
    0.23
    Activations Density 0.008%

    No Known Activations