© 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. 15440
    Prev
    Next
    INDEX
    Explanations

    cricket match results

    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
    dog
    -0.21
    enko
    -0.19
    åĬ¨
    -0.19
    æ¿Ģ
    -0.18
    lett
    -0.18
     Humb
    -0.18
    åħ¥
    -0.17
    å·¡
    -0.17
    system
    -0.17
    ape
    -0.17
    POSITIVE LOGITS
     Facing
    0.20
    éļ¾æĢª
    0.19
    é¢ł
    0.18
    侧éĿ¢
    0.18
    arpa
    0.18
    éĢ»
    0.18
     Assigned
    0.18
    çĥŁçģ«
    0.18
    åĩĨåĪĻ
    0.18
    æĹĹä¸ĭ
    0.18
    Activations Density 0.003%

    No Known Activations