© 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. 2385
    Prev
    Next
    INDEX
    Explanations

    motion animation

    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
    åģĩæĹ¥
    -0.26
    ³»
    -0.24
    æı½
    -0.23
    èIJ¦
    -0.23
    æĸ°åŁİ
    -0.23
     synerg
    -0.22
    rous
    -0.22
    彩
    -0.22
    æľŁåĨħ
    -0.22
    ess
    -0.21
    POSITIVE LOGITS
    éĻ¢å£«
    0.26
     Hast
    0.23
    æŁIJ个
    0.23
     Lig
    0.22
     dequeue
    0.22
    èĢĮ导èĩ´
    0.22
    UGHT
    0.22
     fert
    0.22
     naughty
    0.21
     Neighbor
    0.21
    Activations Density 0.003%

    No Known Activations