© 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. 10596
    Prev
    Next
    INDEX
    Explanations

    finally, Gold, .ViewModel, official

    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
    å¤¸å¼ł
    -0.20
    _CAST
    -0.20
    uous
    -0.20
    åģ¶çĦ¶
    -0.20
    ish
    -0.20
    æѤ类
    -0.19
     unknown
    -0.19
    çĶº
    -0.18
    éķ¿å¯¿
    -0.18
    unknown
    -0.18
    POSITIVE LOGITS
    ç»Īäºİ
    0.35
    çµĤæĸ¼
    0.30
    æŀľçĦ¶
    0.27
    æĢ»ç®Ĺ
    0.26
     finally
    0.25
    æĸ°çļĦä¸Ģ
    0.23
    ä¾ĿçĦ¶æĺ¯
    0.23
    åĽŀæĿ¥äºĨ
    0.23
    第äºĮæī¹
    0.23
    finally
    0.23
    Activations Density 0.287%

    No Known Activations