© 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. 10372
    Prev
    Next
    INDEX
    Explanations

    ns assertion

    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
    ниÑĨ
    -0.17
    oil
    -0.17
    رÙĨ
    -0.17
    ../../../
    -0.16
    oft
    -0.16
    æĻ°
    -0.16
    lore
    -0.15
    ниÑĨа
    -0.15
    aries
    -0.15
    MBOL
    -0.15
    POSITIVE LOGITS
    NewLabel
    0.18
    avorite
    0.16
    ftime
    0.16
    Ø£ÙĪضاع
    0.15
    urve
    0.14
    ptime
    0.14
    sonian
    0.14
    пÑĢоÑĦеÑģÑģионал
    0.13
    ÙĥÙĬ
    0.13
    éļİ
    0.13
    Activations Density 0.778%

    No Known Activations