© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1790
    Prev
    Next
    INDEX
    Explanations

    billion euros per year

    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
    .Par
    -0.25
    ä¸ĢåľĪ
    -0.23
    -exc
    -0.22
     Dess
    -0.22
    åĪ»
    -0.22
    oretical
    -0.21
    åĨ°éĽª
    -0.21
    pecific
    -0.21
    (par
    -0.21
     Osw
    -0.20
    POSITIVE LOGITS
    欧åħĥ
    0.30
     cents
    0.29
     dollars
    0.28
     bucks
    0.27
     euros
    0.26
    èĭ±éķij
    0.26
    ä¸ĩç¾İåħĥ
    0.25
     euro
    0.24
    人æ°ijå¸ģ
    0.24
     جÙĨÙĬÙĩ
    0.23
    Activations Density 0.063%

    No Known Activations