© 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. 12421
    Prev
    Next
    INDEX
    Explanations

    percentage symbol

    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
    jie
    -0.20
    etz
    -0.20
    ike
    -0.19
    (Equal
    -0.19
    WARE
    -0.19
    esen
    -0.19
    éĥĬ
    -0.18
     влад
    -0.18
    æĬ½åĩº
    -0.18
    åĢ©
    -0.18
    POSITIVE LOGITS
    .va
    0.21
    ç»Ŀ大éĥ¨åĪĨ
    0.20
    ç»Ŀ大å¤ļæķ°
    0.19
    edly
    0.19
    ç³ł
    0.19
    巨人
    0.18
    ãģĹãģ¾
    0.18
    弩
    0.18
    åĩłä¹İ没æľī
    0.18
    aan
    0.18
    Activations Density 0.064%

    No Known Activations