© 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. 10652
    Prev
    Next
    INDEX
    Explanations

    Director of

    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
    ä¸Ģå¹ħ
    -0.21
    ä¸Ģ个å°ı
    -0.20
    fighter
    -0.18
    ä¸ĭå·´
    -0.17
    éĤ£ç§į
    -0.17
    å¡ŀ
    -0.17
    èµĽ
    -0.17
    èĢģå¸ĪçļĦ
    -0.17
    è½¼
    -0.17
     anonymity
    -0.17
    POSITIVE LOGITS
    adow
    0.26
    è§ĦåĪĴ设计
    0.20
    icher
    0.20
    迸
    0.20
    ï¼
    0.20
    å¾·èĤ²
    0.19
    管çIJĨå·¥ä½ľ
    0.19
    åīįçŀ»
    0.19
     IndexPath
    0.19
    æĤĮ
    0.19
    Activations Density 0.032%

    No Known Activations