© 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. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 56708
    Prev
    Next
    INDEX
    Explanations

    Snippets of varied text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人åĢij
    -0.37
    人们çļĦ
    -0.35
    人们
    -0.34
    让人们
    -0.32
    让大家
    -0.32
     thousands
    -0.31
     popular
    -0.30
    ä¸ĩåı°
    -0.29
    ogle
    -0.29
     lobby
    -0.28
    POSITIVE LOGITS
    妻åŃIJ
    0.35
    æ¯į亲
    0.34
    çĵ¶
    0.31
     ÑģÑĭн
    0.31
    æĪ¿
    0.29
    女åıĭ
    0.29
    è¿Ļ个人
    0.28
    书æĪ¿
    0.28
    æľ¬äºº
    0.28
    å¨ĺ
    0.28
    Activations Density 0.001%

    No Known Activations