© 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. 14403
    Prev
    Next
    INDEX
    Explanations

    make up

    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
    eous
    -0.16
    ãģıãĤĭ
    -0.16
    uality
    -0.16
    éĤ¸
    -0.15
    /column
    -0.15
    ousse
    -0.15
    ä¸Ģ声
    -0.15
    rett
    -0.15
    级
    -0.15
    ucks
    -0.15
    POSITIVE LOGITS
    ager
    0.18
    nut
    0.18
    åĴĮå®ĮåĸĦ
    0.18
    åľĥ
    0.17
    好çļĦ
    0.17
    ç¼ļ
    0.17
    ped
    0.16
    ç¼
    0.16
    lying
    0.16
    弥补
    0.16
    Activations Density 0.006%

    No Known Activations