© 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. 15867
    Prev
    Next
    INDEX
    Explanations

    click, tap, or button-press actions

    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
    ibbon
    -0.25
    CallableWrapper
    -0.24
    ButtonTitles
    -0.23
    .getvalue
    -0.21
    abyrinth
    -0.21
    ué
    -0.20
    BitFields
    -0.20
    HeaderCode
    -0.20
    PropertyParams
    -0.20
    uros
    -0.19
    POSITIVE LOGITS
     zwyk
    0.20
    为æĬĵ
    0.20
    èIJ½åľ¨
    0.20
     anywhere
    0.20
    point
    0.20
    ä¸įåIJĮçļĦ
    0.19
    POINT
    0.19
    å§ĭäºİ
    0.19
     inne
    0.18
    æĻ®éĢļçļĦ
    0.18
    Activations Density 0.043%

    No Known Activations