© 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. 16767
    Prev
    Next
    INDEX
    Explanations

    home insurance or home games

    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
     parts
    -0.18
    ↵
    -0.17
    -0.17
    å°¸
    -0.17
     lifecycle
    -0.17
    é£İåı£
    -0.17
     Oro
    -0.17
    éĺŁä¼į建设
    -0.17
    ´
    -0.16
     obtain
    -0.16
    POSITIVE LOGITS
    (home
    0.23
    .Home
    0.23
    /home
    0.22
    Ñĩив
    0.21
    /Home
    0.21
    ä½ıåĿĢ
    0.20
    æĦ¦
    0.20
    ðŁıł
    0.20
    nut
    0.19
    .home
    0.19
    Activations Density 0.050%

    No Known Activations