© 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. 14758
    Prev
    Next
    INDEX
    Explanations

    Tampa Bay sports teams

    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
    å²Ļ
    -0.19
     Ñģобой
    -0.19
    оÑī
    -0.19
    èĬ±çĵ£
    -0.19
    rem
    -0.19
    ê²½ìłľ
    -0.18
    头çĸ¼
    -0.17
    веÑĩ
    -0.17
    溪
    -0.17
    é¢Ŀ头
    -0.17
    POSITIVE LOGITS
    iler
    0.20
    eger
    0.20
     forth
    0.20
    esc
    0.19
    çĽ¸ä¼ł
    0.18
    issen
    0.18
    åĦ¿
    0.18
    outh
    0.18
     Monaco
    0.18
    åŃIJ
    0.17
    Activations Density 0.001%

    No Known Activations