© 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. 12349
    Prev
    Next
    INDEX
    Explanations

    moving elsewhere or changing location

    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
    cis
    -0.23
     главное
    -0.19
    ä¸ĢæĬĬ
    -0.19
    æīŃ转
    -0.18
    isol
    -0.18
    typeparam
    -0.18
    羣å®ŀçļĦ
    -0.18
    çĽ²
    -0.18
     avi
    -0.17
    åIJĦè¡ĮåIJĦä¸ļ
    -0.17
    POSITIVE LOGITS
    æĽ¿ä»£
    0.22
    临æŶ
    0.22
     elsewhere
    0.20
    åį®
    0.20
    æįº
    0.20
    ç²Ŀ
    0.20
     Scar
    0.20
    éĻĨ
    0.20
    ç»ķ
    0.19
    绸
    0.19
    Activations Density 0.050%

    No Known Activations