© 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. 12142
    Prev
    Next
    INDEX
    Explanations

    listing property or homes

    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
    alic
    -0.20
    侬
    -0.19
    bare
    -0.19
    æĹ¢æľī
    -0.19
    ze
    -0.19
    ez
    -0.19
    转载请
    -0.19
    综åIJĪå®ŀåĬĽ
    -0.19
     Traff
    -0.18
    为主çļĦ
    -0.18
    POSITIVE LOGITS
    played
    0.20
    æĿĤ
    0.19
    éra
    0.18
     rusty
    0.18
    agree
    0.17
    å¿ħä¸įåı¯
    0.17
    æĿľåħ°
    0.17
    å¼ģ
    0.17
    èIJ§
    0.17
    ä¸įåIJĮæĦı
    0.17
    Activations Density 0.001%

    No Known Activations