© 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. 12125
    Prev
    Next
    INDEX
    Explanations

    aircraft model numbers

    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
    ì
    -0.19
    åħ¨ãģ¦
    -0.17
    inea
    -0.17
    enn
    -0.17
    asio
    -0.17
    ennes
    -0.17
    azzo
    -0.17
    罡
    -0.17
    âķļ
    -0.17
    lage
    -0.16
    POSITIVE LOGITS
    éķĹ
    0.18
    åħ¨æĹ¥åĪ¶
    0.18
    éĻĢ
    0.18
    Ģ
    0.17
    æī¶
    0.17
    >Main
    0.17
    容å¿į
    0.17
    级以ä¸Ĭ
    0.17
    åĽ½åº¦
    0.17
    åįĹè·¯
    0.17
    Activations Density 0.114%

    No Known Activations