© 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. 12149
    Prev
    Next
    INDEX
    Explanations

    parenthood and children

    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
    æĹ¥è®°
    -0.23
    ä¸Ģ件äºĭ
    -0.20
    åĿIJåľ¨
    -0.20
    gni
    -0.17
    ãģŀ
    -0.17
    osity
    -0.17
    æĺ¯ä¸ĢåIJį
    -0.17
    举æŃ¢
    -0.17
    EqualTo
    -0.17
    gres
    -0.16
    POSITIVE LOGITS
    主任
    0.21
    æľºæŀĦ
    0.21
    åħ¨åĽ½
    0.20
    主ä½ĵ
    0.20
    æݧèĤ¡éĽĨåĽ¢
    0.19
     vide
    0.19
    quan
    0.19
    orges
    0.19
     Vi
    0.19
    vero
    0.19
    Activations Density 0.001%

    No Known Activations