© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14953
    Prev
    Next
    INDEX
    Explanations

    media file formats and downloads

    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
    èĢĨ
    -0.23
    npc
    -0.21
    дол
    -0.20
    åı£æ°Ķ
    -0.20
    æľ¬é¢Ĩ
    -0.20
    .datab
    -0.19
    endale
    -0.19
    è¡Ķ
    -0.19
    pcf
    -0.18
    allet
    -0.18
    POSITIVE LOGITS
    ç²¾åĵģ
    0.24
    é«ĺè´¨éĩı
    0.23
     calidad
    0.22
    åİĭ缩
    0.22
    åĪĨ辨çİĩ
    0.21
    è´¨éĩıéĹ®é¢ĺ
    0.21
    åĪĨæł¡
    0.20
    çļĦè´¨éĩı
    0.20
    æł¼å¼ı
    0.20
     ÑĤоÑĢÑĢенÑĤ
    0.20
    Activations Density 0.018%

    No Known Activations