© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10656
    Prev
    Next
    INDEX
    Explanations

    another followed by a noun

    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çĪ±
    -0.23
    åIJĦåİ¿
    -0.20
    akov
    -0.20
    Tank
    -0.20
    两次
    -0.19
    Berry
    -0.19
    beck
    -0.18
     Twice
    -0.18
    oss
    -0.18
    /null
    -0.18
    POSITIVE LOGITS
    ä¸İåħ¶ä»ĸ
    0.31
    ä¸Ģ个æĸ°çļĦ
    0.27
     among
    0.25
    çĮ®
    0.24
    among
    0.23
     ÑģÑĢеди
    0.23
     оÑĩеÑĢед
    0.22
    çį»
    0.21
    çļĦä¸Ģåijĺ
    0.21
    åı¸
    0.20
    Activations Density 0.180%

    No Known Activations