© 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. 11314
    Prev
    Next
    INDEX
    Explanations

    bibliography style specification

    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
    tabpanel
    -0.19
    èĽĭç³ķ
    -0.19
    .compress
    -0.18
     vụ
    -0.18
    edException
    -0.18
    plements
    -0.18
    tright
    -0.18
    .transition
    -0.18
     tec
    -0.18
    emer
    -0.17
    POSITIVE LOGITS
    åIJ¸åıĸ
    0.19
    书ä¸Ń
    0.19
    尤为éĩįè¦ģ
    0.18
    æľ¬æĬ¥
    0.18
    çīĪ
    0.18
    lug
    0.18
     perfor
    0.18
    ä¸Ńæĸ¹
    0.17
     trivial
    0.17
    -ignore
    0.17
    Activations Density 0.011%

    No Known Activations