© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 444
    Prev
    Next
    INDEX
    Explanations

    district court

    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
    .gradle
    -0.24
    -cover
    -0.23
    SCREEN
    -0.23
    æĺŁçº§
    -0.22
     shading
    -0.22
    çłĸ
    -0.22
    _building
    -0.22
     ÑįÑĦÑĦ
    -0.21
    导å¸Ī
    -0.21
     reun
    -0.21
    POSITIVE LOGITS
    unta
    0.27
     Hust
    0.24
     Courts
    0.23
     Cly
    0.23
     jurisdiction
    0.23
     courthouse
    0.22
     Lafayette
    0.22
     lyn
    0.22
     Illinois
    0.22
    èµ·è¯ī
    0.22
    Activations Density 0.067%

    No Known Activations