© 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. 212
    Prev
    Next
    INDEX
    Explanations

    signed artworks

    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
    æŀľ
    -0.24
     ped
    -0.24
    _LAYER
    -0.23
    æ°´æºIJ
    -0.22
    çĿĢæĢ¥
    -0.22
    åı¤æĢª
    -0.21
    æ·¡æ°´
    -0.21
    åĪ°åºķ
    -0.21
     propor
    -0.21
    究竣
    -0.21
    POSITIVE LOGITS
    çIJĥæĺŁ
    0.35
    çŃ¾åIJį
    0.30
    åĪ¶åĵģ
    0.28
     WWE
    0.27
     FIFA
    0.26
     stadium
    0.26
    çī©ä»¶
    0.25
     signings
    0.25
    çī©åĵģ
    0.24
     residue
    0.24
    Activations Density 0.006%

    No Known Activations