© 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. 2283
    Prev
    Next
    INDEX
    Explanations

    bill payments and costs

    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
    lop
    -0.24
     кнопк
    -0.22
    ë§IJ
    -0.22
    throp
    -0.21
    æĬŁ
    -0.21
    law
    -0.21
    filtered
    -0.21
    thus
    -0.20
    bidden
    -0.20
    dm
    -0.20
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.26
    -paying
    0.25
    ÂŃing
    0.23
    è¢ĭ
    0.23
    /console
    0.22
    -answer
    0.22
    累累
    0.22
    çļĦçŃĶæ¡Ī
    0.21
    holder
    0.21
    yard
    0.21
    Activations Density 0.005%

    No Known Activations