© 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. 187
    Prev
    Next
    INDEX
    Explanations

    countries, organizations, or creative works

    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
    æĸ¹æīį
    -0.24
     Duterte
    -0.23
     гоÑĢ
    -0.23
     vers
    -0.21
     ki
    -0.21
     rests
    -0.21
     michael
    -0.21
     outs
    -0.20
    ById
    -0.20
     unwilling
    -0.20
    POSITIVE LOGITS
    åĴĮä»ĸçļĦ
    0.28
    à¸Ĥà¸Ńà¸ĩà¹Ģà¸Ĥา
    0.24
    çĿ£å¯¼
    0.23
    ropy
    0.23
    亲èĩª
    0.23
    Personal
    0.23
     personalize
    0.23
     personally
    0.23
     SPA
    0.22
     MPS
    0.22
    Activations Density 0.241%

    No Known Activations