© 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. 16301
    Prev
    Next
    INDEX
    Explanations

    friendly, efficient, intensive

    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
    äºĮåŃĹ
    -0.18
    éĶĪ
    -0.18
    etter
    -0.18
    ä¸ĸçķĮ级
    -0.17
    urname
    -0.16
    CAC
    -0.16
    éĺIJ
    -0.16
    _pending
    -0.16
     SORT
    -0.16
    CAT
    -0.16
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.23
    åŀĭä¼ģä¸ļ
    0.20
    éĢĶ
    0.20
    åĴĮæĬĢæľ¯
    0.18
    åĴĮ个人
    0.18
    èĭįçĻ½
    0.18
    YTE
    0.17
    æĪĸèĢħ说
    0.17
    ç¾ļ
    0.17
    ï¸ı
    0.17
    Activations Density 0.152%

    No Known Activations