© 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. 12906
    Prev
    Next
    INDEX
    Explanations

    not official yet

    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
    磺
    -0.20
     ìķĦë§Ī
    -0.19
    修订
    -0.18
    ãģ§ãģĤãĤįãģĨ
    -0.18
    brush
    -0.18
    èį·
    -0.17
    mani
    -0.17
     поÑĢ
    -0.17
    æĶ¿åįı
    -0.17
    å¾Ī满æĦı
    -0.17
    POSITIVE LOGITS
    RSS
    0.23
    orra
    0.22
    ale
    0.22
    accent
    0.20
    aron
    0.20
    reed
    0.20
    ilo
    0.20
    Fault
    0.20
    .Serializer
    0.19
    agan
    0.19
    Activations Density 0.017%

    No Known Activations