© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12932
    Prev
    Next
    INDEX
    Explanations

    Pacific Northwest and Alaska, islands

    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
     Niger
    -0.21
     Nigerian
    -0.21
    éĿŀæ´²
    -0.20
     Cyprus
    -0.20
     Abu
    -0.20
    æ´¹
    -0.20
     african
    -0.19
    áºŃu
    -0.19
     Parliamentary
    -0.19
    ijo
    -0.19
    POSITIVE LOGITS
    é²ij
    0.26
    Pacific
    0.25
    -Pacific
    0.23
    太平æ´ĭ
    0.23
    Portland
    0.22
    -Russian
    0.22
    ä¿Ħ
    0.22
    ä¸Ńä¿Ħ
    0.22
     Pacific
    0.22
     Oregon
    0.22
    Activations Density 0.039%

    No Known Activations