© 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. 12405
    Prev
    Next
    INDEX
    Explanations

    KlayGE console output

    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
    亲人
    -0.21
    義
    -0.17
    ighter
    -0.17
    åľ¨å¸Ĥåľºä¸Ĭ
    -0.17
    é»Ħéĩij
    -0.17
    è¾½
    -0.17
    cit
    -0.16
    [file
    -0.16
     RESOURCE
    -0.16
     clips
    -0.16
    POSITIVE LOGITS
    æĪ¬
    0.20
    åѤ
    0.18
     wholesale
    0.18
    纵横
    0.17
    串èģĶ
    0.17
     gut
    0.17
    bold
    0.17
    æĹ¥æľ¬ãģ®
    0.17
    entina
    0.17
    edes
    0.17
    Activations Density 0.001%

    No Known Activations