© 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. 12605
    Prev
    Next
    INDEX
    Explanations

    partial list or collection

    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
    ubar
    -0.20
    runs
    -0.20
     ISSN
    -0.20
    orns
    -0.19
    ооÑĢ
    -0.19
    ør
    -0.19
    åħģ
    -0.18
    ấu
    -0.18
    éĻĦåĬł
    -0.18
    åĿ
    -0.17
    POSITIVE LOGITS
     list
    0.23
    åĪĹ举
    0.21
    说äºĨ
    0.21
    æĥ³äºĨæĥ³
    0.20
     examples
    0.20
    åĪĹ表
    0.20
     liá»ĩt
    0.20
    窥
    0.19
    list
    0.19
    ä»ĭç»į
    0.19
    Activations Density 0.028%

    No Known Activations