© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11843
    Prev
    Next
    INDEX
    Explanations

    toys, dolls, princesses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    åķ¤éħĴ
    -0.22
    ToDevice
    -0.21
    太æŀģ
    -0.20
    举
    -0.20
     Beer
    -0.19
    éļ¼
    -0.19
    æĬĸ
    -0.18
    åIJįçīĩ
    -0.18
     bev
    -0.18
    .twitch
    -0.18
    POSITIVE LOGITS
    女åŃ©
    0.27
     doll
    0.27
    类产åĵģ
    0.24
     Doll
    0.23
    梳
    0.23
     dolls
    0.21
    主é¢ĺæķĻèĤ²
    0.21
    女åŃ©åŃIJ
    0.21
     girl
    0.20
    extr
    0.20
    Activations Density 0.009%

    No Known Activations