© 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. 610
    Prev
    Next
    INDEX
    Explanations

    stars rating

    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
    åľ¨ä¸ĢæĹģ
    -0.22
    _endian
    -0.22
     naked
    -0.21
    .tie
    -0.21
    ä¸ĸ纪
    -0.21
    ÑĤÑĮÑģÑı
    -0.21
     ordin
    -0.21
     variables
    -0.21
    裸
    -0.20
     fib
    -0.20
    POSITIVE LOGITS
    æĪĸå¤ļ
    0.24
    以ä¸ĬçļĦ
    0.24
    allen
    0.22
    ategy
    0.21
    éģİ
    0.21
     Connected
    0.20
    ovsky
    0.20
    以ä¸Ĭ
    0.20
    éĽĨåľĺ
    0.20
     ive
    0.20
    Activations Density 0.004%

    No Known Activations