© 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. 10638
    Prev
    Next
    INDEX
    Explanations

    OAuth 2.0 signorOAuth / oauth 2

    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
    çĺŁ
    -0.19
    ãģĭãģĦ
    -0.19
    RTL
    -0.18
     STAT
    -0.18
    å°ģéĶģ
    -0.18
    顺丰
    -0.18
    é¢ĸ
    -0.18
    sville
    -0.18
    æīĢå¾Ĺ
    -0.17
    _VIRTUAL
    -0.17
    POSITIVE LOGITS
    .partial
    0.26
    è·¨
    0.22
    ä¼ŀ
    0.21
    /oauth
    0.21
    身份
    0.20
    grant
    0.19
    (passport
    0.19
    åŁŁ
    0.19
     partial
    0.18
    姥
    0.18
    Activations Density 0.075%

    No Known Activations