© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15251
    Prev
    Next
    INDEX
    Explanations

    Nebraska cities, states, and associated places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Gow
    -0.22
    æŦ
    -0.21
     GIR
    -0.21
    æ²Ķ
    -0.20
     Gy
    -0.20
     Istanbul
    -0.20
    éĩįåºĨ
    -0.19
    份
    -0.19
     Giz
    -0.19
    ä¸Ģ份
    -0.18
    POSITIVE LOGITS
    éķ¿åŁİ
    0.22
    èĥģ
    0.21
    CAA
    0.21
    ected
    0.20
     Hague
    0.19
    åī²
    0.19
    orses
    0.19
    åŀ©
    0.18
     Nebraska
    0.18
    OLON
    0.18
    Activations Density 0.031%

    No Known Activations