© 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. 13965
    Prev
    Next
    INDEX
    Explanations

    Large Hadron Collider / LHC

    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
    regist
    -0.20
    elves
    -0.18
    åģİ
    -0.18
    >NN
    -0.18
    /logging
    -0.18
    /vnd
    -0.17
    /operators
    -0.17
    -0.17
    ichten
    -0.17
    æĹ¥æĬ¥éģĵ
    -0.17
    POSITIVE LOGITS
     Osama
    0.20
    åĿij
    0.19
    åijķåIJIJ
    0.19
    ä»ij
    0.18
    ä¸įæķ¢
    0.18
     przec
    0.18
    èĥ½æĬĬ
    0.18
    çĪ¬
    0.18
    éĽĨèģļ
    0.18
    AQ
    0.18
    Activations Density 0.006%

    No Known Activations