© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17288
    Prev
    Next
    INDEX
    Explanations

    Middle East

    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
    Negative Logits
    说å®Į
    -0.19
    INGS
    -0.18
    fully
    -0.18
    æµ·åĨħå¤ĸ
    -0.17
    éĹ®ä¸ĸ
    -0.17
    ä»Ģä¹ĪåİŁåĽł
    -0.17
    æŃ¡
    -0.17
    æľŁåĨħ
    -0.17
    mons
    -0.17
    iteit
    -0.17
    POSITIVE LOGITS
    imbus
    0.20
    auge
    0.19
    æľī害
    0.18
    rub
    0.18
    orris
    0.17
    igg
    0.17
    owe
    0.17
    _CONSTANT
    0.17
    oup
    0.16
    rael
    0.16
    Activations Density 0.004%

    No Known Activations