© 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. 13292
    Prev
    Next
    INDEX
    Explanations

    place names and regions

    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
    .soft
    -0.21
    ç»ĨèĬĤ
    -0.18
     impart
    -0.18
    åĮħ
    -0.18
    æĥħæĢĢ
    -0.18
    èĸĦ
    -0.18
    кÑĥÑģ
    -0.18
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.18
    shortcut
    -0.18
    /framework
    -0.18
    POSITIVE LOGITS
     vic
    0.20
    ä¸Ģ带
    0.19
    vic
    0.19
    ugh
    0.19
     genie
    0.18
    嶷
    0.18
    ulls
    0.18
    çĽĨåľ°
    0.18
    inan
    0.18
    ropolitan
    0.18
    Activations Density 0.043%

    No Known Activations