© 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. 2
    Prev
    Next
    INDEX
    Explanations

    been in existence for a duration

    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
    éģĩåĪ°äºĨ
    -0.25
    çīĴ
    -0.24
     Alo
    -0.24
    _TE
    -0.23
    æĸ°çļĦä¸Ģ
    -0.23
    å½ĵä¸ĭ
    -0.23
    åı¯ä»¥åľ¨
    -0.22
    ä¹Łè®©
    -0.22
    ä¹ŁæĪIJ为
    -0.22
    为äºĨ让
    -0.21
    POSITIVE LOGITS
     until
    0.32
     since
    0.31
     decades
    0.29
    缴åĪ°
    0.29
     seit
    0.29
    ä¸Ģ缴åĪ°
    0.28
    足足
    0.28
    since
    0.28
    until
    0.27
    Years
    0.27
    Activations Density 0.161%

    No Known Activations