© 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. 14678
    Prev
    Next
    INDEX
    Explanations

    via

    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
    -0.22
    屿
    -0.20
    ened
    -0.19
    ÑģоÑĤ
    -0.19
    /or
    -0.19
    scribe
    -0.18
    åĽłä¸ºåľ¨
    -0.18
    venge
    -0.17
    £
    -0.17
    åĽłä¸ºä»ĸ
    -0.17
    POSITIVE LOGITS
    ogh
    0.26
    /out
    0.20
    èĩ¾
    0.18
    ç§įç§į
    0.18
    “
    0.17
    ä¸įæĸŃçļĦ
    0.17
    ä½ķç§į
    0.16
     اÙĦØ¥ÙĨترÙĨت
    0.16
    ä¸įæĸŃåľ°
    0.16
    è¿Ļç§įæĸ¹å¼ı
    0.16
    Activations Density 0.044%

    No Known Activations