© 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. 1712
    Prev
    Next
    INDEX
    Explanations

    costs and expenses

    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
    .ast
    -0.23
     Peripheral
    -0.23
     Synopsis
    -0.23
    颤
    -0.23
     VARIANT
    -0.23
    çݦ
    -0.22
    OUND
    -0.22
    é¢Į
    -0.22
     tame
    -0.22
    ãģ¾ãģķ
    -0.22
    POSITIVE LOGITS
    æĪIJæľ¬
    0.45
    çļĦæĪIJæľ¬
    0.44
     cost
    0.44
     costs
    0.42
    è´¹çĶ¨
    0.41
     costo
    0.41
     cheapest
    0.39
     Cost
    0.39
     expenses
    0.38
    _cost
    0.38
    Activations Density 0.505%

    No Known Activations