© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 16571
    Prev
    Next
    INDEX
    Explanations

    carotene, granzyme, histone, chlorophyll, compressor wheel

    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
    æ°IJ
    -0.20
    çݰè¡Į
    -0.20
    eson
    -0.20
    åĪ©äºļ
    -0.19
     Sey
    -0.19
    åı¯ä¿¡
    -0.19
    姤
    -0.18
    æĿĥçĽĬ
    -0.18
    éĶĦ
    -0.18
    驼
    -0.18
    POSITIVE LOGITS
     trad
    0.22
    ç͍æĿ¥
    0.22
    trad
    0.22
    åı¸
    0.21
    .TRA
    0.20
    éĢģæĿ¥
    0.20
    ä»İèĢĮ
    0.19
    ä¸Ģ家人
    0.19
    ridged
    0.19
    MOVED
    0.19
    Activations Density 0.304%

    No Known Activations