© 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. 12511
    Prev
    Next
    INDEX
    Explanations

    here is

    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
    ä¸įåIJĮç¨ĭ度
    -0.21
    ä¹ĭæĦı
    -0.20
    çİĭèĢħ
    -0.20
    ocale
    -0.19
    ÑĢÑĥÑĩ
    -0.18
    uggle
    -0.18
    ijing
    -0.17
    ä¸ĢéŨ
    -0.17
    Guide
    -0.17
    ypy
    -0.17
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.34
    ä¸ĭéĿ¢
    0.29
    ä¸ĭéĿ¢å°±
    0.28
    ä¸ĭéĿ¢æĪij们
    0.25
    ä¸ĭéĿ¢æĺ¯
    0.25
     ниже
    0.24
    below
    0.24
     below
    0.24
    Below
    0.23
    å½ķ
    0.22
    Activations Density 0.228%

    No Known Activations