© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    credit card

    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
    aidu
    -0.24
     Overall
    -0.23
    öh
    -0.23
    âģ¿
    -0.23
    aro
    -0.22
     Suitable
    -0.21
     intervened
    -0.21
    æľĢåħ³éĶ®
    -0.21
    累积
    -0.21
    太æ¹ĸ
    -0.21
    POSITIVE LOGITS
     pager
    0.23
    ä¼ı
    0.23
    æĪĸåħ¶ä»ĸ
    0.22
    eam
    0.22
    æĪĸ
    0.21
    ATS
    0.21
    AMI
    0.21
    Haz
    0.21
    飨
    0.21
    /AP
    0.21
    Activations Density 0.003%

    No Known Activations