© 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. 13550
    Prev
    Next
    INDEX
    Explanations

    police officers, departments, spokesman

    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
    sWith
    -0.18
    ãģĦãģŁãĤī
    -0.17
    tests
    -0.17
    èĢģ人家
    -0.17
    à¹Ĩ
    -0.17
    åĦ¿
    -0.17
    tempt
    -0.16
    listeners
    -0.16
    ensity
    -0.16
    æĮijåīĶ
    -0.16
    POSITIVE LOGITS
    ye
    0.20
    yy
    0.18
    gia
    0.18
    åijĺ
    0.17
    kie
    0.17
    人åijĺ
    0.17
    ya
    0.17
    åŃ¦å®¶
    0.17
    oj
    0.16
    åĵ¡
    0.16
    Activations Density 0.019%

    No Known Activations