© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2918
    Prev
    Next
    INDEX
    Explanations

    I mean followed by explanation

    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
    ä¹Łå°±æĺ¯
    -0.29
     viz
    -0.27
    åı¦å¤ĸ
    -0.27
    æѤå¤ĸ
    -0.26
    coe
    -0.26
    以ä¸ĭæĺ¯
    -0.26
    ä¸ºä½ł
    -0.25
     nevertheless
    -0.25
    åĽłæѤ
    -0.25
     nonetheless
    -0.24
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.32
    æ¯ķç«Ł
    0.31
     obviously
    0.30
    çķ¢ç«Ł
    0.28
     obvious
    0.27
     famously
    0.24
    驹
    0.24
     rarely
    0.24
    没è§ģè¿ĩ
    0.24
    ight
    0.23
    Activations Density 0.018%

    No Known Activations