© 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. 13069
    Prev
    Next
    INDEX
    Explanations

    Japanese media and characters

    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
    melon
    -0.21
    /widgets
    -0.20
    ality
    -0.18
    -widgets
    -0.18
    OrCreate
    -0.18
    éĴĩ
    -0.18
    ä¸Ģé¢Ĺ
    -0.18
    毫
    -0.17
    ãģ«åIJijãģijãģ¦
    -0.17
    åĨį说
    -0.17
    POSITIVE LOGITS
    æ±ģ
    0.20
    è¹ĩ
    0.19
     weekends
    0.18
    éŀŃ
    0.18
    å¿«æĬ¥
    0.18
     shortcut
    0.18
    éķ¿å¤§
    0.18
    车éģĵ
    0.17
    åIJı
    0.17
    éĻĭ
    0.17
    Activations Density 0.001%

    No Known Activations