© 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. 11227
    Prev
    Next
    INDEX
    Explanations

    diversity of

    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
    ä¸įä½ı
    -0.18
    ters
    -0.17
    乡æĿijæĮ¯åħ´
    -0.17
    plit
    -0.16
    ä¸įéĢļ
    -0.15
    pler
    -0.15
    eland
    -0.15
    æ°ª
    -0.15
     vicinity
    -0.15
    伸åĩº
    -0.15
    POSITIVE LOGITS
    -minded
    0.20
    nel
    0.19
    ä¸Ĭå²Ĺ
    0.18
    ulle
    0.17
    tro
    0.17
    èł¡
    0.16
     spont
    0.16
    -aware
    0.16
    ä¼Ļ
    0.16
    etti
    0.15
    Activations Density 0.020%

    No Known Activations