© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3129
    Prev
    Next
    INDEX
    Explanations

    concealing, conceiving, conceal

    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
    åIJ¹
    -0.23
     lover
    -0.22
    è¾IJ
    -0.22
    åĹĵ
    -0.21
    æ»ĭ润
    -0.21
    æĸĩåŃĹ
    -0.21
    å¿IJ
    -0.21
    ç´ł
    -0.21
    åħħåĢ¼
    -0.21
     Gos
    -0.21
    POSITIVE LOGITS
    tü
    0.22
    lung
    0.22
    gmt
    0.21
    tures
    0.21
    èĥ½æĬĬ
    0.21
    /dom
    0.21
    ystems
    0.21
    é²¥
    0.20
    Managed
    0.20
    Mgr
    0.20
    Activations Density 0.003%

    No Known Activations