© 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. 10906
    Prev
    Next
    INDEX
    Explanations

    information content data

    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
     iNdEx
    -0.23
     uLocal
    -0.22
    /grpc
    -0.21
    éĻIJæľŁ
    -0.21
    鸷
    -0.21
    quo
    -0.20
    æĿŀ
    -0.20
    $input
    -0.20
    ritz
    -0.20
    FilterWhere
    -0.20
    POSITIVE LOGITS
    åĨħ容
    0.32
     contents
    0.26
     content
    0.26
    ä¿¡æģ¯
    0.25
     ÑģодеÑĢж
    0.25
    åħ§å®¹
    0.24
    çļĦåĨħ容
    0.23
    content
    0.23
    contents
    0.22
     information
    0.22
    Activations Density 0.280%

    No Known Activations