© 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. 13502
    Prev
    Next
    INDEX
    Explanations

    job and task descriptions

    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
    æĢĿ绪
    -0.20
    åīįæīĢ
    -0.19
    çŃĿ
    -0.18
    æĬ±åĽ¢
    -0.18
    rot
    -0.17
    便äºİ
    -0.17
    locals
    -0.17
    é««
    -0.17
    (logging
    -0.17
    åĨľçĶ°
    -0.17
    POSITIVE LOGITS
    èī°å·¨
    0.25
    çļĦä»»åĬ¡
    0.23
    èģĮè´£
    0.23
     task
    0.22
    ä»»åĬ¡
    0.20
     tasks
    0.20
    å°±æĺ¯è¦ģ
    0.20
     duties
    0.20
    /task
    0.19
    sell
    0.19
    Activations Density 0.053%

    No Known Activations