© 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. 329
    Prev
    Next
    INDEX
    Explanations

    last few years/decades

    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
     ultimately
    -0.33
    å½ĵæĹ¥
    -0.32
    å½ĵæŶçļĦ
    -0.31
     someday
    -0.31
     eventually
    -0.30
     later
    -0.29
    æľĢç»Ī
    -0.29
     eventual
    -0.28
    åIJİæĿ¥
    -0.28
     ultimate
    -0.27
    POSITIVE LOGITS
    以æĿ¥
    0.37
    以ä¾Ĩ
    0.35
    çļĦæŶéĹ´éĩĮ
    0.31
    ä¸ĢçĽ´åľ¨
    0.30
    éĻĨç»Ń
    0.29
    åĩłæ¬¡
    0.27
    since
    0.27
    rapid
    0.26
     since
    0.26
    æ¶Įçİ°åĩº
    0.26
    Activations Density 0.066%

    No Known Activations