© 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. 12945
    Prev
    Next
    INDEX
    Explanations

    "AS IS" BASIS

    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
     «
    -0.34
    ãĢĮ
    -0.31
    ãĢĤãĢĮ
    -0.28
     “
    -0.28
    ï¼ļ“
    -0.27
    “A
    -0.27
     ãĢĮ
    -0.27
     “âĢ¦
    -0.26
    ãĢģãĢĮ
    -0.23
     “[
    -0.23
    POSITIVE LOGITS
    ”çļĦ
    0.31
    ãĢįãģ¨
    0.29
    ï½£
    0.27
    âĢĽ
    0.24
    âĪ½
    0.24
    ãĢĭ
    0.23
     (*)
    0.22
    ”ï¼Į
    0.21
    ãĢį
    0.21
    ãĢı
    0.20
    Activations Density 1.754%

    No Known Activations