© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    rankings and positions

    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
    éĤ£äºº
    -0.24
    ality
    -0.23
     raining
    -0.23
     Hom
    -0.23
     Rain
    -0.22
     symp
    -0.22
    -aut
    -0.22
     geared
    -0.21
    ä¸įå¼Ģ
    -0.21
     Commission
    -0.21
    POSITIVE LOGITS
    æİĴåIJį
    0.39
     rankings
    0.38
     positions
    0.35
    åľ°ä½į
    0.34
     standings
    0.34
     ranks
    0.33
    大å¹ħ度
    0.33
    ä½įç½®
    0.31
    æĶĢåįĩ
    0.31
     ranking
    0.31
    Activations Density 0.031%

    No Known Activations