© 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. 12538
    Prev
    Next
    INDEX
    Explanations

    4

    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
     fer
    -0.21
    TE
    -0.19
     Fer
    -0.18
    è¦ı模
    -0.18
    çľī
    -0.17
    èĢĮæĪIJ
    -0.17
    俱
    -0.17
    ä¾®
    -0.17
    æ½ŀ
    -0.17
     INTERN
    -0.17
    POSITIVE LOGITS
    ढ
    0.21
    .present
    0.19
    xda
    0.18
    ç½ijç»ľä¼łæĴŃ
    0.18
    empo
    0.18
    æĬ¢åįł
    0.18
    ingly
    0.17
    DET
    0.17
    BuilderFactory
    0.17
    gne
    0.17
    Activations Density 0.054%

    No Known Activations