© 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. 3025
    Prev
    Next
    INDEX
    Explanations

    lamp and lighting devices

    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
    tures
    -0.24
    TING
    -0.22
    ted
    -0.21
     enlarged
    -0.21
    eing
    -0.19
    emed
    -0.19
    tle
    -0.19
    ìłģìľ¼ë¡ľ
    -0.19
    éĺ²èĮĥ
    -0.19
     ÐŁÐ¾Ñĩем
    -0.19
    POSITIVE LOGITS
    shade
    0.34
    itude
    0.24
    ellation
    0.24
    inal
    0.23
    inality
    0.22
    ä¸ĢåĽŀäºĭ
    0.21
    éĵĽ
    0.21
    achine
    0.21
    shaft
    0.21
    urai
    0.20
    Activations Density 0.008%

    No Known Activations