© 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. 12776
    Prev
    Next
    INDEX
    Explanations

    numbers and specific entities

    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
    åĪ°æŶåĢĻ
    -0.27
    秣æĪ¿
    -0.20
    ä»ħä¾Ľ
    -0.20
    è¨ĵ
    -0.19
    èĮ¯
    -0.19
     unins
    -0.19
     sober
    -0.18
    Ñĥни
    -0.18
    COR
    -0.18
    ç¡Į
    -0.18
    POSITIVE LOGITS
     AppModule
    0.21
    éĢŁ
    0.20
    è¦ģåѦä¼ļ
    0.20
    精彩çļĦ
    0.20
     trailing
    0.19
    appers
    0.19
    åıįå¼¹
    0.19
     HttpMethod
    0.19
    示èĮĥåĮº
    0.19
    isted
    0.18
    Activations Density 0.001%

    No Known Activations