© 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. 11889
    Prev
    Next
    INDEX
    Explanations

    you followed by a word

    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
    åIJ¦
    -0.24
    æĪĸå¤ļ
    -0.23
    æĪĸå°Ĩ
    -0.22
    calar
    -0.20
    Ñĩа
    -0.20
    åħļçļĦé¢Ĩ导
    -0.20
    alah
    -0.20
    .GetObject
    -0.19
    igte
    -0.18
    让åѦçĶŁ
    -0.18
    POSITIVE LOGITS
    Via
    0.20
    家éķ¿ä»¬
    0.19
    acci
    0.19
    .ids
    0.19
    å¥ī
    0.19
    置身
    0.19
    è¯ļæĦı
    0.19
    ä¸ĢæŃ¥ä¸ĢæŃ¥
    0.18
    ä¼ĺéĽħ
    0.18
    Mic
    0.18
    Activations Density 0.043%

    No Known Activations