© 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. 3069
    Prev
    Next
    INDEX
    Explanations

    town hall seat

    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
    dr
    -0.22
    ãģĦãĤĭãģ¨
    -0.21
    di
    -0.21
    åľºåIJĪ
    -0.20
    -0.20
    ÑĩÑijÑĤ
    -0.20
    éĺŁéķ¿
    -0.20
    ght
    -0.19
    daf
    -0.19
    nyder
    -0.19
    POSITIVE LOGITS
    iday
    0.28
    mates
    0.27
    ships
    0.26
    mate
    0.24
    arity
    0.23
    ware
    0.23
    igram
    0.22
    itory
    0.22
    zap
    0.21
    istry
    0.20
    Activations Density 0.008%

    No Known Activations