© 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. 2741
    Prev
    Next
    INDEX
    Explanations

    state official titles

    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
    æĦıè§ģåıįé¦Ī
    -0.26
    ç»ĵæŀĦè°ĥæķ´
    -0.25
    anter
    -0.24
    Tower
    -0.23
    nings
    -0.22
    客æĪ¿
    -0.22
    istik
    -0.22
    ç¦ģåĮº
    -0.21
    çĹħæĪ¿
    -0.21
     Crusher
    -0.21
    POSITIVE LOGITS
     Elections
    0.31
     voter
    0.30
     electoral
    0.30
     ballot
    0.30
    éĢī举
    0.29
     election
    0.27
     elections
    0.27
    æĬķ票
    0.27
     Electoral
    0.26
    paced
    0.26
    Activations Density 0.020%

    No Known Activations