© 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. 2937
    Prev
    Next
    INDEX
    Explanations

    travel destinations and accommodations

    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
    metro
    -0.29
     Computer
    -0.28
     Pub
    -0.27
     bench
    -0.26
     freeway
    -0.26
    计ç®Ĺæľº
    -0.26
    ç»Ĭ
    -0.26
    Computer
    -0.25
    滥çĶ¨
    -0.25
    鼶件
    -0.24
    POSITIVE LOGITS
    éĩİå¤ĸ
    0.30
    æīĵçĮİ
    0.29
    丼æŀĹ
    0.28
     bespoke
    0.28
     malaria
    0.28
    çĶŁæħĭ
    0.28
    æĹĸ
    0.28
    æ°ij宿
    0.28
    åºĦåĽŃ
    0.27
    寨
    0.27
    Activations Density 0.020%

    No Known Activations