© 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. 2854
    Prev
    Next
    INDEX
    Explanations

    social media connections and actions

    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
    æĭ¿åĩºæĿ¥
    -0.24
    ftime
    -0.24
    泪水
    -0.23
    æµ´
    -0.23
     pouring
    -0.23
    icot
    -0.22
    sst
    -0.22
    æĬĹçĶŁç´ł
    -0.22
    ÅŁe
    -0.21
    bred
    -0.21
    POSITIVE LOGITS
     whom
    0.28
    交å¾Ģ
    0.28
    åIJįåįķ
    0.27
    /twitter
    0.26
    人æķ°
    0.25
    åIJį
    0.24
    åħ³ç³»
    0.23
     relationships
    0.23
    /watch
    0.23
     åIJį
    0.23
    Activations Density 0.022%

    No Known Activations