© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3273
    Prev
    Next
    INDEX
    Explanations

    reuse and recycling

    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
    Negative Logits
    ãģŀ
    -0.27
     foss
    -0.24
    åĩºè½¨
    -0.23
    ahr
    -0.23
    éĿŀæ³ķ
    -0.23
    èīºæľ¯å®¶
    -0.23
    åģıåIJij
    -0.22
    æİĮ
    -0.22
    acas
    -0.22
     Friedrich
    -0.22
    POSITIVE LOGITS
     reuse
    0.46
    reuse
    0.41
     recycling
    0.39
     reused
    0.36
    Reuse
    0.35
    åºŁå¼ĥ
    0.34
     disposal
    0.34
     recycle
    0.33
     recycled
    0.32
    åºŁçī©
    0.30
    Activations Density 0.042%

    No Known Activations