© 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. 858
    Prev
    Next
    INDEX
    Explanations

    architectural styles, revivals, art deco, bauhaus, mid-century

    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
    æĿ¥è®¿
    -0.23
    亩
    -0.22
    åıĭæĥħéĵ¾æİ¥
    -0.22
    æ§IJ
    -0.22
     Lisp
    -0.21
    ãģĬãģı
    -0.21
    loating
    -0.21
    åĮĹæĸ¹
    -0.21
     paren
    -0.21
     volont
    -0.21
    POSITIVE LOGITS
    -era
    0.42
    é£İæł¼
    0.33
    -style
    0.27
    æĹ¶ä»£çļĦ
    0.26
    æĹ¶æľŁ
    0.26
    -ish
    0.25
    -esque
    0.25
    -inspired
    0.25
     structures
    0.25
     era
    0.25
    Activations Density 0.006%

    No Known Activations