© 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. 14097
    Prev
    Next
    INDEX
    Explanations

    football and soccer positions

    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
    æľ¬äºĭ
    -0.20
    æĮĽ
    -0.19
    electron
    -0.18
     thảo
    -0.18
     Pom
    -0.17
    cob
    -0.17
    头æĻķ
    -0.17
    .chapter
    -0.17
    ä¸ŃæľŁ
    -0.17
    vely
    -0.17
    POSITIVE LOGITS
    _masks
    0.20
    åľ¨åIJĮä¸Ģ
    0.19
    éĺµåľ°
    0.19
    åIJĪæ³ķ
    0.19
     fou
    0.18
    çİ°å®ŀçĶŁæ´»
    0.18
    æ¯ķä¸ļåIJİ
    0.17
    触åıĬ
    0.17
    èľī
    0.17
    æij
    0.17
    Activations Density 0.005%

    No Known Activations