© 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. 13
    Prev
    Next
    INDEX
    Explanations

    plays and characters

    np_acts-logits-general · gemini-2.5-flash-lite

    references to well-known classic literary, theatrical, and operatic works, including their titles and character/role names.

    oai_token-act-pair · gpt-5Triggered by @adamkarvonen
    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
     dislikes
    -0.24
    bmp
    -0.24
    ç¼ĥ
    -0.24
     manh
    -0.23
     spins
    -0.23
     Fla
    -0.23
    plied
    -0.23
    ç©¿è¡£
    -0.23
     swell
    -0.23
    ç½ijå°ıç¼ĸ
    -0.22
    POSITIVE LOGITS
    æĪĺåľºä¸Ĭ
    0.24
    .Execution
    0.23
    åĭĸ
    0.23
    侥幸
    0.23
    recht
    0.23
     using
    0.22
    çİĭæľĿ
    0.22
    âĢİ
    0.22
    åıĤè°ĭ
    0.21
     coached
    0.21
    Activations Density 0.008%

    No Known Activations