© 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. 13688
    Prev
    Next
    INDEX
    Explanations

    dot org, dot com, than

    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
    æĬĬä»ĸ
    -0.19
    reland
    -0.19
    otten
    -0.18
    oose
    -0.18
    sWith
    -0.18
    ague
    -0.18
    antu
    -0.17
    éĶ·
    -0.17
    (skb
    -0.17
    angu
    -0.17
    POSITIVE LOGITS
     minus
    0.23
     miscellaneous
    0.21
    ä»Ģä¹Īåij¢
    0.20
    çŃīäºİ
    0.19
    åı·
    0.19
     plus
    0.18
    è´¼
    0.17
     ÑĢавно
    0.17
    è¿Ļ家åħ¬åı¸
    0.17
     пÑĢоб
    0.17
    Activations Density 0.192%

    No Known Activations