© 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. 12546
    Prev
    Next
    INDEX
    Explanations

    stamping, embossing, spring-boot, deployment, beetle

    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
    aic
    -0.23
     Richie
    -0.20
    å¸Ń
    -0.20
    _ICON
    -0.19
     Radical
    -0.18
    ignant
    -0.18
     metro
    -0.18
     tán
    -0.17
     radical
    -0.17
    女主
    -0.17
    POSITIVE LOGITS
    filer
    0.21
    errick
    0.21
    æĭĽåĭŁ
    0.19
     gql
    0.19
    rå
    0.19
    бÑĥ
    0.19
    _globals
    0.18
     Skywalker
    0.18
    æIJ
    0.18
    é¦ĸè½®
    0.18
    Activations Density 0.006%

    No Known Activations