© 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. 13806
    Prev
    Next
    INDEX
    Explanations

    function definitions or keywords

    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
    åĮĸ
    -0.23
    uman
    -0.20
    alc
    -0.20
    ç¹ģ
    -0.20
    æ²»
    -0.19
    MLE
    -0.19
    æīĩ
    -0.19
    -encoded
    -0.18
    èĪª
    -0.18
    åįĥéĩĮ
    -0.18
    POSITIVE LOGITS
    /ay
    0.21
    åı¬åĶ¤
    0.20
    å¤§éĽ¨
    0.20
    è´ŀ
    0.20
    妹
    0.19
    sip
    0.19
     Hạ
    0.18
    èįª
    0.18
    æĿ¥æī¾
    0.18
    éĴµ
    0.18
    Activations Density 0.027%

    No Known Activations