© 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. 1838
    Prev
    Next
    INDEX
    Explanations

    car makes and models

    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
    ten
    -0.27
    æ¨Ł
    -0.25
     Buddhist
    -0.24
    bis
    -0.23
    濯
    -0.23
    ç¦ħ
    -0.22
    sono
    -0.22
    顺丰
    -0.22
     Sheffield
    -0.22
    nga
    -0.22
    POSITIVE LOGITS
    缴è¾ĸ
    0.27
     ComVisible
    0.27
     Belle
    0.26
    轿车
    0.25
    éĩįå·¥
    0.24
    约ä¼ļ
    0.24
    缴å±ŀ
    0.24
    amac
    0.23
    .dll
    0.23
    IDL
    0.23
    Activations Density 0.011%

    No Known Activations