© 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. 11186
    Prev
    Next
    INDEX
    Explanations

    names starting with ' Flint' or ' Clint'

    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
     wr
    -0.19
     arrivals
    -0.17
    ndl
    -0.17
     Abbey
    -0.16
    anel
    -0.16
    duk
    -0.16
    lı
    -0.16
    INAL
    -0.16
     rais
    -0.15
    apol
    -0.15
    POSITIVE LOGITS
    erness
    0.20
    çĿĽ
    0.18
    stones
    0.17
    æ´¥
    0.17
    ãģĹãģ¾ãģĦ
    0.17
    ä¸įåģľåľ°
    0.17
     babys
    0.17
    ä¸įåłª
    0.16
     Samar
    0.16
    æľīæĦıæĢĿ
    0.16
    Activations Density 0.002%

    No Known Activations