© 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. 10898
    Prev
    Next
    INDEX
    Explanations

    utm_source or Recommended Citation

    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
    å§ĭç»Īä¿ĿæĮģ
    -0.26
    collision
    -0.20
    æĩĤ
    -0.19
     elong
    -0.19
    _RESERVED
    -0.19
    åªĸ
    -0.18
    å¹³æ°ij
    -0.18
    åħ¨åijĺ
    -0.18
     eskort
    -0.18
    amage
    -0.18
    POSITIVE LOGITS
     UNU
    0.23
    å®ıè§Ĥç»ıæµİ
    0.21
     econ
    0.20
    èļ¤
    0.20
    æľŁåĪĬ
    0.20
    stanbul
    0.20
    çªĸ
    0.20
    论æĸĩ
    0.20
    ä¹Łåı¯èĥ½
    0.20
    åĽļ
    0.19
    Activations Density 0.020%

    No Known Activations