© 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. 13061
    Prev
    Next
    INDEX
    Explanations

    belgian people and places

    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
    ownik
    -0.17
    icular
    -0.17
    leigh
    -0.17
    imony
    -0.17
    ķ
    -0.16
    bones
    -0.16
    omic
    -0.16
    around
    -0.16
    izontal
    -0.16
    edin
    -0.15
    POSITIVE LOGITS
    ãģĩ
    0.20
    popover
    0.17
    amp
    0.16
    大家ä¸Ģèµ·
    0.16
    ister
    0.15
    toast
    0.15
    antine
    0.15
    uster
    0.15
    _AST
    0.14
    rijk
    0.14
    Activations Density 0.011%

    No Known Activations