© 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. 11773
    Prev
    Next
    INDEX
    Explanations

    money and costs

    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
    伸æīĭ
    -0.20
    车éģĵ
    -0.19
    åĬ¨æīĭ
    -0.19
    æĶ¾æīĭ
    -0.18
    åĨľåī¯äº§åĵģ
    -0.18
    å®ĹæŨ
    -0.18
    __/
    -0.18
    çļĦæĥ³æ³ķ
    -0.18
    Ide
    -0.18
    unque
    -0.18
    POSITIVE LOGITS
    èģĺ请
    0.23
    ä¸įåģľ
    0.22
    éľĩ
    0.20
    åĨ²æ´Ĺ
    0.19
    iddy
    0.19
    强è¡Į
    0.19
    å¾Ĺèµ·
    0.19
    åıªä¸º
    0.18
     Kaplan
    0.18
     Bradley
    0.18
    Activations Density 0.033%

    No Known Activations