© 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. 3087
    Prev
    Next
    INDEX
    Explanations

    city names

    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
    ä¸ĢåĪĩ
    -0.26
    esome
    -0.24
    ugi
    -0.23
    -plugins
    -0.23
     seas
    -0.22
    oins
    -0.22
     bef
    -0.21
    oire
    -0.21
     reap
    -0.21
    ocalypse
    -0.21
    POSITIVE LOGITS
    蹦
    0.23
    æķ°æį®æĺ¾ç¤º
    0.22
     JAVA
    0.22
     Irving
    0.22
    åĶ§
    0.21
    ÙģÙĦ
    0.21
     Quant
    0.21
    å¤ļä½ĻçļĦ
    0.21
     :",
    0.21
    串
    0.21
    Activations Density 0.130%

    No Known Activations