© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14969
    Prev
    Next
    INDEX
    Explanations

    suppliers and parts

    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
    roys
    -0.21
    yro
    -0.21
     squash
    -0.20
    EOS
    -0.20
    åİĨåı²æĸ°
    -0.20
    Mixin
    -0.19
    约è°Ī
    -0.19
    è¿·æĥij
    -0.19
    COND
    -0.19
    instagram
    -0.19
    POSITIVE LOGITS
    ä¾Ľç»Ļ
    0.30
    ä¾ĽåºĶ
    0.29
    æĬĢæľ¯æľįåĬ¡
    0.26
     supplying
    0.26
    æĬĢæľ¯åĪĽæĸ°
    0.25
    åįĸç»Ļ
    0.24
    产åĵģ
    0.24
    çī¯
    0.23
    åĴĮæľįåĬ¡
    0.21
    æł¸å¿ĥæĬĢæľ¯
    0.21
    Activations Density 0.257%

    No Known Activations