© 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. 14345
    Prev
    Next
    INDEX
    Explanations

    scores and statistics

    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
    adies
    -0.20
    elloworld
    -0.19
     Burning
    -0.19
    igor
    -0.19
    åļ
    -0.19
    iminal
    -0.19
    tain
    -0.19
    èĩ³æѤ
    -0.18
    寸
    -0.18
    .None
    -0.18
    POSITIVE LOGITS
    çŃĿ
    0.21
    ç¼Ł
    0.19
    ç¾İéºĹ
    0.19
    çĦ¦
    0.19
    ç»Łè®¡
    0.18
    çIJĨå·¥
    0.18
    ä¿Ŀåģ¥
    0.18
    讦
    0.18
    Iterations
    0.18
    ç§ĥ
    0.18
    Activations Density 0.002%

    No Known Activations