© 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. 2232
    Prev
    Next
    INDEX
    Explanations

    to check out

    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
    soever
    -0.25
    /vnd
    -0.24
     hopefully
    -0.23
    isoft
    -0.23
     frankly
    -0.23
     presumably
    -0.22
    ç®ĢçĽ´å°±æĺ¯
    -0.22
    æĹłçĸijæĺ¯
    -0.22
    个å¤ļ
    -0.22
     suddenly
    -0.22
    POSITIVE LOGITS
    íŀĪ
    0.28
    çķĻæĦı
    0.28
    æıIJåĪ°
    0.26
    çıįæĥľ
    0.24
    æľīä¸ĢäºĽ
    0.24
    带ä¸Ĭ
    0.24
    注æĦı
    0.24
    认æ¸ħ
    0.24
     mention
    0.24
     Disclaimer
    0.23
    Activations Density 0.013%

    No Known Activations