© 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. 12775
    Prev
    Next
    INDEX
    Explanations

    preppy, modern, sophisticated, style

    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
    å¸ĪçĶŁ
    -0.21
    ERING
    -0.21
    à¤Ŀ
    -0.20
    imator
    -0.19
    _contents
    -0.19
    çŁ¥å·±
    -0.19
    ände
    -0.19
    èĤīç±»
    -0.18
    åħ¨æĸĩ
    -0.18
    ruc
    -0.18
    POSITIVE LOGITS
    æ°Ķè´¨
    0.22
    æ°Ķæģ¯
    0.21
     yet
    0.21
     style
    0.20
    yet
    0.20
    ãĤ¹ãĤ¿ãĤ¤ãĥ«
    0.20
     quotient
    0.20
    style
    0.20
    _STYLE
    0.20
    Style
    0.20
    Activations Density 0.031%

    No Known Activations