© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 944
    Prev
    Next
    INDEX
    Explanations

    physical and chemical properties

    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
     Gos
    -0.25
    ä¹ĭæĥħ
    -0.23
    åįłæľī
    -0.23
    åħ·æľīèī¯å¥½
    -0.23
    ihu
    -0.22
    éĢģ
    -0.22
    DU
    -0.22
    æŶåĪ»
    -0.22
    ucceeded
    -0.21
     Dix
    -0.21
    POSITIVE LOGITS
    æĺ¯å¤ļå°ij
    0.44
    æľĢé«ĺçļĦ
    0.40
    è¶Ĭé«ĺ
    0.40
    ä¸įé«ĺ
    0.38
    太é«ĺ
    0.36
    é«ĺçļĦ
    0.36
    å¾Īé«ĺçļĦ
    0.36
    è¾ĥé«ĺçļĦ
    0.35
    å¾Īä½İ
    0.34
    è¾ĥä½İ
    0.34
    Activations Density 0.887%

    No Known Activations