© 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. 11231
    Prev
    Next
    INDEX
    Explanations

    Premier League

    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
    ر
    -0.17
    aday
    -0.16
    ered
    -0.16
    ãģĹãģ¾
    -0.16
    ÙĪØ·
    -0.15
    ENC
    -0.15
    onical
    -0.15
    ernal
    -0.15
    äºŃ
    -0.15
    ŀ
    -0.14
    POSITIVE LOGITS
    ing
    0.24
    ities
    0.23
    esse
    0.21
     Ñģобой
    0.20
    ises
    0.20
    es
    0.19
    ement
    0.19
    ized
    0.18
    جاÙĨ
    0.18
    ize
    0.18
    Activations Density 0.007%

    No Known Activations