© 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. 11043
    Prev
    Next
    INDEX
    Explanations

    but without

    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
     Bund
    -0.20
    ç²ĺ
    -0.19
    edom
    -0.19
    çİĸ
    -0.19
    æĭ·
    -0.18
     Completely
    -0.18
    too
    -0.18
     Minds
    -0.18
    éĩįçĤ¹
    -0.18
    kop
    -0.18
    POSITIVE LOGITS
    æīĢæıIJä¾ĽçļĦ
    0.21
    ãģ¨ãģĵãĤįãģ§
    0.20
    å°½åĬĽ
    0.20
    Accuracy
    0.19
    鸵
    0.19
    讵
    0.19
    æĭĸæ¬ł
    0.18
    ä½ĨçĶ±äºİ
    0.18
    £¼
    0.18
    ãģ¤ãĤĤãĤĬ
    0.18
    Activations Density 0.058%

    No Known Activations