© 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. 2448
    Prev
    Next
    INDEX
    Explanations

    health conditions and people needing care

    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
    æĺİæĻº
    -0.22
    »¿
    -0.22
    ıè¿°
    -0.21
    è§Ħ模æľĢ大
    -0.21
    \Framework
    -0.21
     '**
    -0.21
     ("<
    -0.21
    aidu
    -0.20
    .Designer
    -0.20
    åIJĦè¡ĮåIJĦä¸ļ
    -0.20
    POSITIVE LOGITS
    æĢ¥éľĢ
    0.35
     urgently
    0.29
    æĢ¥
    0.28
    èĢģ人
    0.28
    äºŁ
    0.27
    æĹłäºº
    0.27
    çĸ¾çĹħ
    0.26
     urgent
    0.26
     condition
    0.26
     requiring
    0.26
    Activations Density 0.047%

    No Known Activations