© 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. 15713
    Prev
    Next
    INDEX
    Explanations

    4x relay, olympics, athlete

    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
    èħ¹
    -0.21
    çīĩåŃIJ
    -0.20
    ิà¸ģ
    -0.20
    thesis
    -0.20
    ç¯ĩ
    -0.19
    esis
    -0.18
    èĤ¯
    -0.18
     Nghá»ĭ
    -0.18
     ep
    -0.18
    ç¼Ł
    -0.17
    POSITIVE LOGITS
    æİ¥åĬĽ
    0.23
    ฯ
    0.19
    æ³ħ
    0.19
    ennial
    0.19
    Latin
    0.18
    å¹´åīį
    0.18
    apid
    0.18
    ollen
    0.17
    athlete
    0.17
    åĵĢ
    0.17
    Activations Density 0.004%

    No Known Activations