© 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. 11892
    Prev
    Next
    INDEX
    Explanations

    sometimes

    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
    们çļĦ
    -0.19
    缮åīįå·²ç»ı
    -0.19
    ãģ¾ãģļãģ¯
    -0.18
    æľ¬æľĪ
    -0.18
    ãģ¾ãģķ
    -0.18
    们
    -0.18
    sume
    -0.17
    æĹłçĸij
    -0.17
    è°ħ
    -0.17
    OTE
    -0.17
    POSITIVE LOGITS
     xuyên
    0.27
    -times
    0.25
    侯
    0.25
    ìĶ©
    0.23
    åĢĻ
    0.21
    -used
    0.20
    EDA
    0.19
    -ending
    0.19
     ÙĬÙĥÙĪÙĨ
    0.18
    greens
    0.18
    Activations Density 0.021%

    No Known Activations