© 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. 119
    Prev
    Next
    INDEX
    Explanations

    refrigerants and carbon compounds

    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
    _horizontal
    -0.27
    è¯Ĺè¯į
    -0.25
     downhill
    -0.25
    æµģæ°´
    -0.25
    odb
    -0.24
     Poetry
    -0.24
    ERIC
    -0.24
    æ¸ħæ°´
    -0.24
    è¯Ĺ
    -0.23
     poetry
    -0.23
    POSITIVE LOGITS
    åĪ¶åĨ·
    0.39
     refriger
    0.39
     gases
    0.30
    éģ¿åŃķ
    0.30
     Refriger
    0.28
    æ°Ķä½ĵ
    0.27
    溴
    0.26
    è¡¥
    0.26
    éĶĢæ¯ģ
    0.26
     leaks
    0.26
    Activations Density 0.028%

    No Known Activations