© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15026
    Prev
    Next
    INDEX
    Explanations

    government positions like president or governor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     ALT
    -0.20
    èľļ
    -0.20
    åĽºå®ļçļĦ
    -0.19
    REN
    -0.18
    èī¯å¥½çļĦ
    -0.18
    ustin
    -0.17
    å§IJ
    -0.17
    èĢķ
    -0.17
    reed
    -0.17
     reload
    -0.17
    POSITIVE LOGITS
    æ¹ĺ
    0.21
    æ½®æµģ
    0.19
    /gin
    0.18
    éĥ¨åī¯
    0.18
    失败
    0.18
    念头
    0.18
     glac
    0.17
     Att
    0.17
    åıijåĬ¨æľº
    0.17
    æ½ľ
    0.17
    Activations Density 0.025%

    No Known Activations