© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 324
    Prev
    Next
    INDEX
    Explanations

    access to rooms and places

    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
    ä¸ĩåı°
    -0.24
    target
    -0.23
    æĤ¬
    -0.23
    imei
    -0.23
    ä¸ĩ个
    -0.23
    sted
    -0.23
    irl
    -0.22
    è´µéĩijå±ŀ
    -0.22
    iant
    -0.22
    targets
    -0.22
    POSITIVE LOGITS
    缸éĢļ
    0.34
     Seam
    0.32
     directly
    0.32
     kitchen
    0.30
    äºĮ楼
    0.29
    åݨæĪ¿
    0.29
     hallway
    0.29
    æ¯ĹéĤ»
    0.28
     Küche
    0.28
     accessed
    0.27
    Activations Density 0.017%

    No Known Activations