© 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. 235
    Prev
    Next
    INDEX
    Explanations

    place names or proper nouns

    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
    æµ·æ´ĭ
    -0.58
    æµ·åŁŁ
    -0.54
    æµ·åºķ
    -0.53
     marine
    -0.52
    æµ·ä¸Ĭ
    -0.50
     ocean
    -0.49
    æµ·æ°´
    -0.48
    海滩
    -0.47
    æµ·è¾¹
    -0.47
     shore
    -0.47
    POSITIVE LOGITS
    é«ĺåľ°
    0.26
    çĩİ
    0.26
    è¾Ĺ
    0.24
     Bieber
    0.24
    èĮ¶åĽŃ
    0.23
    èĭķ
    0.23
    çĩł
    0.23
     Pax
    0.23
    èĩ¼
    0.23
     pow
    0.22
    Activations Density 0.607%

    No Known Activations