© 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. 15288
    Prev
    Next
    INDEX
    Explanations

    code changes or new submissions

    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
     VP
    -0.19
     Concepts
    -0.19
    å°±çŁ¥éģĵ
    -0.19
    lus
    -0.19
     Mich
    -0.19
    è°·
    -0.18
    صÙĦا
    -0.18
    LANG
    -0.18
    ä¸Ģç³»åĪĹ
    -0.17
    èĢĮæĪIJ
    -0.17
    POSITIVE LOGITS
    ä¸Ģå¾ĭ
    0.32
    éĻ¤å¤ĸ
    0.28
    å¦Ĥæľī
    0.26
    ä»ħä¾Ľ
    0.24
    çīĪæĿĥå½Ĵ
    0.23
    请èģĶç³»
    0.22
    ä»ħä¾ĽåıĤèĢĥ
    0.21
    ä¸įåı¯ä»¥
    0.21
    ä»»ä½ķå½¢å¼ı
    0.21
    ä»»ä½ķ人
    0.21
    Activations Density 0.093%

    No Known Activations