© 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. 1010
    Prev
    Next
    INDEX
    Explanations

    equity and business transactions

    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
    site
    -0.26
    uction
    -0.21
    abouts
    -0.21
    ugh
    -0.21
    out
    -0.21
    sville
    -0.21
    ın
    -0.20
    лага
    -0.20
    ../
    -0.20
    ä¸įåĩºæĿ¥
    -0.20
    POSITIVE LOGITS
    人士
    0.30
     minded
    0.24
    holders
    0.23
    -wise
    0.21
    -driven
    0.21
    ties
    0.21
    plex
    0.20
    -focused
    0.20
    -minded
    0.20
    -rich
    0.20
    Activations Density 0.004%

    No Known Activations