© 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. 138
    Prev
    Next
    INDEX
    Explanations

    awards and rankings excellence

    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
     vaguely
    -0.26
    éĶĻè¿ĩ
    -0.25
     paralle
    -0.24
     cursed
    -0.24
    åĩłæ¬¡
    -0.24
    æķĻè®Ń
    -0.23
     dần
    -0.23
    éĻIJ度
    -0.23
     enlarg
    -0.23
    ä¸Ģä¼ļåĦ¿
    -0.23
    POSITIVE LOGITS
    综åIJĪå®ŀåĬĽ
    0.41
     excellence
    0.36
    åįĵè¶Ĭ
    0.32
    管çIJĨæ°´å¹³
    0.31
     rankings
    0.31
     consistently
    0.30
    åĪĽæĸ°èĥ½åĬĽ
    0.29
    综åIJĪç´łè´¨
    0.29
     evaluated
    0.29
    ä¼ĺå¼Ĥ
    0.29
    Activations Density 0.050%

    No Known Activations