© 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. 10857
    Prev
    Next
    INDEX
    Explanations

    names and syllables

    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
    çĽ¹
    -0.20
    èģĶéĤ¦
    -0.19
    åĴĸåķ¡
    -0.19
    fox
    -0.19
    ë§Ŀ
    -0.18
    åĨ°ç®±
    -0.18
    åºŁæ°´
    -0.18
     nghá»ģ
    -0.18
    reuse
    -0.18
    .dex
    -0.18
    POSITIVE LOGITS
    åı¤ä»£
    0.29
     Ancient
    0.28
    åı¤
    0.24
     ancient
    0.23
    æĸĽ
    0.21
    åı¤èĢģçļĦ
    0.21
    umer
    0.20
    æĺĨ
    0.20
    å¸ĮèħĬ
    0.20
    æĬ¤æłı
    0.20
    Activations Density 0.181%

    No Known Activations