© 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. 3213
    Prev
    Next
    INDEX
    Explanations

    city council and government roles

    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
    acus
    -0.27
    inders
    -0.25
    OfType
    -0.23
    éĵ¤
    -0.23
    eking
    -0.22
    ipur
    -0.22
    -generation
    -0.22
    ough
    -0.22
    ely
    -0.21
     respective
    -0.21
    POSITIVE LOGITS
    ä¸Ĭä¸ĭ
    0.23
    ä¸ĵåĪ©
    0.23
     bonds
    0.23
    æĸĩ件
    0.22
    çī©
    0.22
    åĬ¡
    0.22
    Outline
    0.22
    æ¦ĤåĨµ
    0.21
    (NS
    0.21
    ä¸ĭçļĦ
    0.21
    Activations Density 0.133%

    No Known Activations