© 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. 12917
    Prev
    Next
    INDEX
    Explanations

    ends of

    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
    cly
    -0.20
    uration
    -0.20
    /downloads
    -0.19
    汩
    -0.19
    -minded
    -0.18
    èݪ
    -0.18
    åºķçĽĺ
    -0.17
    ordes
    -0.17
    鸨
    -0.17
    tor
    -0.17
    POSITIVE LOGITS
    åĦ¿
    0.25
    ãĤĴè¿İ
    0.23
    解æĶ¾æĢĿæĥ³
    0.19
    好
    0.19
    Millis
    0.19
    LESS
    0.19
    sWith
    0.18
    ä¿Ŀ
    0.18
    less
    0.18
     lee
    0.18
    Activations Density 0.031%

    No Known Activations