© 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. 3393
    Prev
    Next
    INDEX
    Explanations

    login to internal systems

    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
     Manufacturer
    -0.30
    /effects
    -0.26
    asers
    -0.26
     Manufacturers
    -0.26
    JsonValue
    -0.26
    大åŁİå¸Ĥ
    -0.26
    _countries
    -0.26
    åľ¨æĪijåĽ½
    -0.25
     chocolates
    -0.25
     YYSTACK
    -0.24
    POSITIVE LOGITS
     campus
    0.40
    æķĻèģĮå·¥
    0.36
     login
    0.35
    åIJĦéĥ¨éŨ
    0.35
     system
    0.34
     service
    0.34
    åħ¨æł¡
    0.34
     workstation
    0.33
     administrative
    0.33
     staff
    0.33
    Activations Density 0.088%

    No Known Activations