© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15295
    Prev
    Next
    INDEX
    Explanations

    generate

    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
    ç½ijé¦ĸ页
    -0.23
    ç½ij讯
    -0.21
    æĩ¦
    -0.19
    åį³ä¾¿æĺ¯
    -0.18
    fab
    -0.18
    ä¸īåĨľ
    -0.18
    ä¸ŃåįĪ
    -0.18
     influ
    -0.18
    ç¼£
    -0.17
    ä¸Ĭå²Ĺ
    -0.17
    POSITIVE LOGITS
    çĽĺ
    0.21
    æīĭç»Ń
    0.20
    .future
    0.19
    è´¿
    0.19
    ichi
    0.19
    å¼Ľ
    0.18
    æºIJæºIJ
    0.18
    _stream
    0.18
    ç«¥
    0.18
     shr
    0.18
    Activations Density 0.002%

    No Known Activations