© 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. 15520
    Prev
    Next
    INDEX
    Explanations

    there are

    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
    ç½²
    -0.20
    çļĦåIJĦç§į
    -0.20
    çĤ¹äºĨ
    -0.20
    ме
    -0.19
    æĶ¾å¿ĥ
    -0.18
    çļĦ主è¦ģ
    -0.18
    å°ıå°ıçļĦ
    -0.18
    èĥ½æĬĬ
    -0.18
    åŃĹ
    -0.18
    åIJĦç§į
    -0.18
    POSITIVE LOGITS
    defs
    0.21
     Visitor
    0.19
    owan
    0.19
    访
    0.19
    threads
    0.18
    à¹Ĥà¸ķ
    0.18
     crown
    0.18
    Visitor
    0.18
    ÑĢев
    0.18
     Crown
    0.18
    Activations Density 0.013%

    No Known Activations