© 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. 1702
    Prev
    Next
    INDEX
    Explanations

    geographical locations and states

    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
    çĶŁäº§ä¼ģä¸ļ
    -0.23
    cab
    -0.22
     Kou
    -0.22
     пÑĢоведен
    -0.22
    Clause
    -0.22
    DBC
    -0.21
    踵
    -0.21
     Observable
    -0.21
     nude
    -0.21
    /account
    -0.21
    POSITIVE LOGITS
     iconic
    0.24
     ubiquitous
    0.23
     famously
    0.23
     Master
    0.22
    Master
    0.22
    _Master
    0.22
     notoriously
    0.22
    ãģĤãģ®
    0.22
    MASTER
    0.22
    åIJİéĿ¢çļĦ
    0.21
    Activations Density 0.999%

    No Known Activations