© 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. 14511
    Prev
    Next
    INDEX
    Explanations

    temporal position

    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
    人为
    -0.21
    çľĭæĿ¥
    -0.20
    çĿ£åĬŀ
    -0.19
    åī¯ç§ĺ书éķ¿
    -0.19
    å®ī举
    -0.19
    çĿ£
    -0.18
    æĪŁ
    -0.18
     åķ
    -0.18
    ician
    -0.18
     <!--[
    -0.18
    POSITIVE LOGITS
    ä¸įè¿ľå¤Ħ
    0.34
     nearby
    0.31
     neighboring
    0.25
     elsewhere
    0.25
     previous
    0.24
     Previous
    0.22
     preceding
    0.22
     ÑģоÑģед
    0.22
    åīįæĸ¹
    0.21
    åĪļæīį
    0.21
    Activations Density 0.231%

    No Known Activations