© 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. 16215
    Prev
    Next
    INDEX
    Explanations

    number of games, goals, points, or wins

    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
    æľīçļĦ
    -0.20
    ä»Ĭ天çļĦ
    -0.20
    AGED
    -0.20
    .cent
    -0.19
    ç¥Ŀ
    -0.19
    äºĭ
    -0.19
    ocaust
    -0.18
    æľīä¸įåIJĮçļĦ
    -0.18
     MES
    -0.18
    èĢ½
    -0.18
    POSITIVE LOGITS
    éħIJ
    0.21
    txn
    0.19
    çĸijéļ¾
    0.19
    ︿
    0.19
    èĥ³
    0.19
    åĬ©æĶ»
    0.18
    åħ³èģĶ交æĺĵ
    0.18
    åĥį
    0.18
    ASK
    0.17
    踯
    0.17
    Activations Density 0.004%

    No Known Activations