© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    applications

    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
    ific
    -0.23
    memo
    -0.22
    éĶĩ
    -0.20
    éķ¥
    -0.20
    abyrinth
    -0.19
    bum
    -0.18
     allot
    -0.18
     hoping
    -0.18
     laure
    -0.18
    fulness
    -0.18
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.35
    åºĶçĶ¨åľºæĻ¯
    0.32
    åľºåIJĪ
    0.31
     applications
    0.30
    åºĶçĶ¨
    0.29
    ä¸Ńå°ıåŀĭ
    0.29
    applications
    0.28
     Applications
    0.28
    ä¸Ńå°ı
    0.27
    åIJĦè¡ĮåIJĦä¸ļ
    0.27
    Activations Density 0.336%

    No Known Activations