© 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. 1892
    Prev
    Next
    INDEX
    Explanations

    architectural materials and styles

    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
    ç£ģåľº
    -0.29
    è¡Ģç³ĸ
    -0.28
    è¡Ģ液
    -0.28
    车åĨħ
    -0.28
     room
    -0.26
    æł·åĵģ
    -0.26
    åľ¨åºĬä¸Ĭ
    -0.25
    åĿIJ
    -0.25
    bubble
    -0.25
    å¸Ń
    -0.24
    POSITIVE LOGITS
    å¤ĸå¢Ļ
    0.45
    ç«ĭéĿ¢
    0.43
     faç
    0.39
     facade
    0.38
     weather
    0.38
    /weather
    0.35
    å¢Ļä½ĵ
    0.33
     architectural
    0.32
    建çŃijçī©
    0.32
    weather
    0.32
    Activations Density 0.034%

    No Known Activations