© 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. 16739
    Prev
    Next
    INDEX
    Explanations

    password reset

    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
     [/
    -0.19
    rogen
    -0.19
    .wikipedia
    -0.18
    (coeff
    -0.18
     Kr
    -0.18
    ä¸Ģ页
    -0.18
     Dem
    -0.18
    å«ĺ
    -0.17
    eral
    -0.17
    AdminController
    -0.17
    POSITIVE LOGITS
    æĸ°åŁİ
    0.21
    è¶ĬæĿ¥
    0.21
    æįŁä¼¤
    0.20
    æĪIJçĨŁ
    0.20
     Jub
    0.20
     дог
    0.20
     pur
    0.20
    ä¸ĵä¸ļåĮĸ
    0.20
    -format
    0.19
    ä¸Ĭæ¼Ķ
    0.19
    Activations Density 0.002%

    No Known Activations