© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    place names ending in "bar" or "sus"

    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
    iage
    -0.26
    horn
    -0.23
    容åĻ¨
    -0.23
    æµ·æ´ĭ
    -0.22
     cá
    -0.22
    ä»ĩ
    -0.21
    头èĦij
    -0.21
    è¦ģ说
    -0.20
     tv
    -0.20
    corn
    -0.20
    POSITIVE LOGITS
    éĹ¨ç¥¨
    0.36
    éĻĦè¿ijçļĦ
    0.33
    æĻ¯åĮº
    0.32
     nearby
    0.29
    æīĢåľ¨åľ°
    0.28
    éĻĦè¿ij
    0.26
    åħ¥åľº
    0.26
    éģĹåĿĢ
    0.26
    orer
    0.25
    ħ§
    0.24
    Activations Density 0.008%

    No Known Activations