© 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. 14577
    Prev
    Next
    INDEX
    Explanations

    HP

    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
    纶
    -0.20
    æ±´
    -0.18
    onus
    -0.17
    岸边
    -0.16
    lor
    -0.16
    lined
    -0.16
    åı£è¢ĭ
    -0.16
    arti
    -0.16
    ally
    -0.16
    ooks
    -0.15
    POSITIVE LOGITS
    elling
    0.17
    GEST
    0.16
    ÑİÑĤ
    0.16
     Catalyst
    0.15
    ï¸ı
    0.15
    Ħ
    0.15
    æĸĩç«łæĿ¥æºIJ
    0.15
    æĶ¹åıĺäºĨ
    0.15
    èĥ³
    0.15
    WSTR
    0.15
    Activations Density 0.013%

    No Known Activations