© 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. 14037
    Prev
    Next
    INDEX
    Explanations

    numbers or symbols

    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
    opp
    -0.20
    åľ¨äº¬
    -0.19
    亲
    -0.19
    ä¸Ģ次
    -0.18
    mony
    -0.17
    ä¸Ģ次次
    -0.17
    ians
    -0.17
    æłĬ
    -0.17
     enc
    -0.17
    çļĦç¨ĭ度
    -0.17
    POSITIVE LOGITS
    .Arguments
    0.20
     à¹Ĩ
    0.18
    KeyCode
    0.18
    лаÑĤ
    0.17
    urrences
    0.17
    à¹Ĩ
    0.17
    .newaxis
    0.17
    arti
    0.17
    æħ¢æħ¢çļĦ
    0.17
    olly
    0.17
    Activations Density 0.029%

    No Known Activations