© 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. 631
    Prev
    Next
    INDEX
    Explanations

    drilling holes

    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
    åIJĮäºĭ们
    -0.22
     Tape
    -0.21
    front
    -0.20
    æĭħ
    -0.20
     tense
    -0.20
     setContent
    -0.20
    çĿ¡
    -0.20
     metam
    -0.20
     Push
    -0.19
     Presenter
    -0.19
    POSITIVE LOGITS
     holes
    0.28
     hole
    0.26
    缴å¾Ħ
    0.26
    éļĻ
    0.25
     drilled
    0.25
    åŃĶ
    0.25
    å¿ĥçĸ¼
    0.24
    帮åĬ©ä¼ģä¸ļ
    0.24
    æľºæ²¹
    0.24
    hole
    0.23
    Activations Density 0.026%

    No Known Activations