© 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. 11063
    Prev
    Next
    INDEX
    Explanations

    key to success

    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
    æĿĤçī©
    -0.19
    åħħå½ĵ
    -0.18
    SCR
    -0.18
    éĹ¼
    -0.18
    澡
    -0.18
    æĢħ
    -0.18
    ä»·ä½į
    -0.18
    诮
    -0.17
    çݯå¢ĥä¸ĭ
    -0.17
    æł·åŃIJ
    -0.17
    POSITIVE LOGITS
    åľ¨äºİ
    0.33
    æĪIJåĬŁ
    0.29
    å°±åľ¨äºİ
    0.25
    æĪIJåĬŁçļĦ
    0.23
     lies
    0.23
    æī¾åĪ°
    0.22
    è¯Ģ
    0.22
    ç§ĺè¯Ģ
    0.22
     success
    0.22
    ä¿ĿæĮģ
    0.21
    Activations Density 0.023%

    No Known Activations