© 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. 12412
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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¸Ģ个å°ıæŶ
    -0.21
    GRA
    -0.21
    çļĦä¸ĢéĿ¢
    -0.20
    .hom
    -0.19
    emente
    -0.19
    AndView
    -0.19
    NSE
    -0.19
    bote
    -0.18
     réussi
    -0.18
    éģĹçķĻ
    -0.18
    POSITIVE LOGITS
    åĭ¿
    0.20
    èĩ³æѤ
    0.19
    ixer
    0.19
    ä¸İæѤ
    0.19
    AMI
    0.18
    åħĥ
    0.18
    åħ¨ä½ĵ
    0.18
    åį³
    0.17
    åĬŀ
    0.17
    ama
    0.17
    Activations Density 0.029%

    No Known Activations