© 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. 16659
    Prev
    Next
    INDEX
    Explanations

    lost followed by noun

    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
    serter
    -0.19
    ETERS
    -0.18
     xuyên
    -0.17
    zelf
    -0.17
     trần
    -0.17
    å®ŀéĻħè¡ĮåĬ¨
    -0.17
    uated
    -0.17
    /sm
    -0.16
    aho
    -0.16
    atura
    -0.16
    POSITIVE LOGITS
    KeySpec
    0.20
    ä¹ĭ乡
    0.19
    å·²ä¹ħçļĦ
    0.19
    ä¹ĭæĹħ
    0.18
    ness
    0.17
     ÑĢанее
    0.17
    ä¹ĭ声
    0.16
    åĽŀé¦ĸ
    0.16
    inand
    0.16
    ä¸İåıijå±ķ
    0.16
    Activations Density 0.017%

    No Known Activations