© 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. 12683
    Prev
    Next
    INDEX
    Explanations

    analog-related words

    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
    ening
    -0.26
    ened
    -0.22
    iness
    -0.22
    aley
    -0.20
    napshot
    -0.20
    olan
    -0.17
    edException
    -0.17
    imulator
    -0.17
    otle
    -0.17
    tlement
    -0.17
    POSITIVE LOGITS
    ues
    0.23
    ously
    0.19
    ä¸įä¸Ĭ
    0.19
    леж
    0.18
    æĢ§å¼º
    0.17
    iliar
    0.17
    Ñĩик
    0.16
    uego
    0.16
    伸åĩº
    0.16
    arith
    0.16
    Activations Density 0.037%

    No Known Activations