© 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. 1654
    Prev
    Next
    INDEX
    Explanations

    named after scientists or discoveries

    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
     Hardcore
    -0.27
     Mojo
    -0.26
     district
    -0.25
     Noir
    -0.24
     scar
    -0.24
     gallery
    -0.24
     inner
    -0.24
     voters
    -0.24
     destination
    -0.24
     costs
    -0.24
    POSITIVE LOGITS
    åıijæĺİ
    0.51
    ç§ijåŃ¦å®¶
    0.48
     inventions
    0.41
    åħ¬è®¤
    0.40
     pioneers
    0.40
    诺è´Ŀå°Ķ
    0.40
     Nobel
    0.39
     discoveries
    0.39
     inventor
    0.38
    天æīį
    0.38
    Activations Density 0.252%

    No Known Activations