© 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. 14908
    Prev
    Next
    INDEX
    Explanations

    began his career or activity

    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
    à¸Ĺร
    -0.20
    veau
    -0.19
     compound
    -0.19
    æ²½
    -0.18
     ÑĦак
    -0.18
    åħ¶ä»ĸ人
    -0.18
    _AUDIO
    -0.18
    ä½łä¼ļåıijçİ°
    -0.18
     ÑģенÑĤ
    -0.17
     RESERVED
    -0.17
    POSITIVE LOGITS
    ä»»èģĮ
    0.23
    å±ħä½ı
    0.22
    æľįå½¹
    0.22
    å¤ļå¹´çļĦ
    0.22
    å¨ħ
    0.20
    çĺģ
    0.19
    years
    0.19
    alias
    0.19
     decades
    0.19
    åĽ¡
    0.19
    Activations Density 0.205%

    No Known Activations