© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 310
    Prev
    Next
    INDEX
    Explanations

    social media

    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
    tures
    -0.25
    ettle
    -0.23
    ä¸ĭåįĬ
    -0.21
    éĹ³
    -0.21
    errar
    -0.21
    TURE
    -0.20
    åİŁæĿ¥æĺ¯
    -0.20
    edd
    -0.20
     solemn
    -0.20
    å¾Ĺä½ı
    -0.20
    POSITIVE LOGITS
    /mobile
    0.25
    /social
    0.25
    -related
    0.25
    /facebook
    0.24
     platforms
    0.23
     campaigns
    0.23
     feeds
    0.23
    -friendly
    0.23
    .facebook
    0.22
    Instagram
    0.22
    Activations Density 0.006%

    No Known Activations