© 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. 14647
    Prev
    Next
    INDEX
    Explanations

    list item separators

    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
    eger
    -0.20
    èıģ
    -0.18
    assin
    -0.18
    .mj
    -0.18
    antes
    -0.18
    è¿ĩåħ³
    -0.18
    arn
    -0.18
     fit
    -0.18
    .mu
    -0.17
    unched
    -0.17
    POSITIVE LOGITS
    å¤ĩçĶ¨
    0.19
     chap
    0.19
    åįģåħ«å±Ĭ
    0.18
    åľ¨åIJĮä¸Ģ
    0.18
    ä¸įæĩĤ
    0.18
    Patterns
    0.18
    ä»İå°ıå°±
    0.18
    åѦ龸
    0.17
    ä½ľåĩºäºĨ
    0.17
    åĮĹ大
    0.17
    Activations Density 0.191%

    No Known Activations