© 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. 13656
    Prev
    Next
    INDEX
    Explanations

    textiles, fabric, sewing, garment, clothing

    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
    æĴ¬
    -0.26
    æĸ§
    -0.23
    ç½į
    -0.20
    preced
    -0.20
    usting
    -0.19
    çĽı
    -0.19
    ænd
    -0.19
    éħ¹
    -0.18
    ift
    -0.18
    itte
    -0.18
    POSITIVE LOGITS
    è¡£æľį
    0.40
    è¡£çī©
    0.39
    æľįè£ħ
    0.37
    ç»ĩ
    0.37
    éĿ¢æĸĻ
    0.36
    ä¸Ŀ绸
    0.34
    纺ç»ĩ
    0.33
     clothing
    0.33
    çªĹå¸ĺ
    0.30
    çļĦè¡£æľį
    0.30
    Activations Density 0.120%

    No Known Activations