© 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. 18-TRANSCODER-HP
    7. 88301
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings/endings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    橱
    -0.27
    岸
    -0.27
    è·Łå¥¹
    -0.26
     rat
    -0.25
    .addAction
    -0.25
     eens
    -0.25
    æ¼±
    -0.24
     Rate
    -0.24
    对她
    -0.24
    Pe
    -0.23
    POSITIVE LOGITS
     Beard
    0.28
     convin
    0.27
    为主线
    0.26
     wides
    0.25
    æĹ¶ä»£ä¸ŃåĽ½
    0.24
     devote
    0.24
    å¸Ŀ
    0.24
    社
    0.24
    wid
    0.24
    ıģı
    0.24
    Activations Density 4.371%

    No Known Activations